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

    Neuronpedia

    INDEX
    Explanations

    emotions and expressions of positivity or negativity related to experiences

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

    preceding a clause

    np_acts-logits-general · gemini-2.0-flash

    specially or especially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StateToProps
    -0.56
    "—
    -0.50
     extraneous
    -0.49
    []
    -0.49
    RRect
    -0.48
     flé
    -0.48
    qrstuvwxyz
    -0.47
     opérateur
    -0.47
    loway
    -0.47
     confidentialité
    -0.47
    POSITIVE LOGITS
     coz
    0.86
     sebab
    0.84
     compare
    0.83
     specially
    0.82
     actually
    0.78
     cause
    0.77
     moreover
    0.76
     especially
    0.73
    specially
    0.72
     comparing
    0.71
    Act Density 0.262%

    No Known Activations