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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to oneself or a group

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that indicate personal involvement or perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peak
    -0.66
     Sung
    -0.62
    advertisement
    -0.59
     Wake
    -0.58
     Governors
    -0.56
    tains
    -0.56
     Relief
    -0.55
    iversary
    -0.55
     AU
    -0.54
     School
    -0.53
    POSITIVE LOGITS
     hereby
    0.98
    'll
    0.94
     nevertheless
    0.86
     reasoned
    0.84
    byss
    0.77
     sugg
    0.76
    reditary
    0.74
     wondered
    0.73
    'd
    0.72
    've
    0.71
    Act Density 0.299%

    No Known Activations