Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to completeness and essential elements in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phrases about finishing or completing something

    np_acts-logits-general · gemini-2.0-flash

    completing or finishing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BigNumberish
    -0.58
     useHistory
    -0.57
    ENEFITS
    -0.56
    SequentialGroup
    -0.56
    ngrx
    -0.54
    uttosto
    -0.53
     mapStateToProps
    -0.52
     destructor
    -0.50
    landa
    -0.49
    findpost
    -0.48
    POSITIVE LOGITS
     completes
    2.07
     completing
    1.85
     Completing
    1.79
     complete
    1.77
     rounding
    1.72
    complete
    1.68
     completed
    1.66
    Comple
    1.65
     Complete
    1.64
    Complete
    1.63
    Act Density 0.218%

    No Known Activations