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

    Neuronpedia

    INDEX
    Explanations

    prepositions, specifically the word "in"

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

    submitting information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wicidata
    -0.57
    SourceChecksum
    -0.52
    kém
    -0.51
     Moly
    -0.49
     canst
    -0.48
    uvwxyz
    -0.48
    DebuggerNonUser
    -0.48
     opti
    -0.48
     Pata
    -0.46
    хьтан
    -0.46
    POSITIVE LOGITS
     submitted
    0.69
     submission
    0.63
     submit
    0.61
     submitting
    0.59
     submits
    0.57
     submissions
    0.57
    submit
    0.56
    Submitting
    0.55
     Submit
    0.54
    Submit
    0.51
    Act Density 0.014%

    No Known Activations