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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    actions and decisions related to help and intervention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ove
    -0.61
    ann
    -0.60
    joining
    -0.60
    omach
    -0.59
    covered
    -0.59
    rafted
    -0.59
    ln
    -0.58
    ãĥ¼ãĥĨãĤ£
    -0.58
    rive
    -0.57
     GN
    -0.57
    POSITIVE LOGITS
     anymore
    0.78
    ãĢĤ
    0.75
     ¯
    0.74
    ?:
    0.69
     defensively
    0.67
     loud
    0.66
    !,
    0.66
    ,''
    0.64
     Afgh
    0.64
    ãħĭãħĭ
    0.63
    Act Density 0.541%

    No Known Activations