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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions that may involve decision-making or moral judgment

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to opportunities and willingness to help or engage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mourning
    -0.59
     Miscellaneous
    -0.58
     Worse
    -0.57
    phans
    -0.56
     Survivors
    -0.56
    igmat
    -0.55
     Governors
    -0.55
     tarn
    -0.54
    neum
    -0.54
     Revelations
    -0.54
    POSITIVE LOGITS
     gladly
    1.02
    ."
    0.82
     accordingly
    0.81
    .''
    0.81
    starter
    0.80
    !
    0.80
    !.
    0.78
    brainer
    0.77
    .
    0.77
    ."[
    0.77
    Act Density 0.867%

    No Known Activations