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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to individuals or groups, as well as past and present participles

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that indicate subject references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Amen
    -0.66
     Additional
    -0.59
     unspecified
    -0.58
    itol
    -0.58
     undisclosed
    -0.58
     guiActiveUnfocused
    -0.57
    "}],"
    -0.57
     sizeof
    -0.56
     whichever
    -0.56
     attribution
    -0.54
    POSITIVE LOGITS
    've
    1.07
     certainly
    0.97
    'll
    0.93
    'd
    0.93
    gemony
    0.88
    're
    0.87
     didn
    0.86
    resy
    0.83
    miah
    0.83
    reditary
    0.83
    Act Density 0.290%

    No Known Activations