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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "end"

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms indicating conclusions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egu
    -0.50
    arching
    -0.50
    efe
    -0.46
    appropriately
    -0.45
    umbn
    -0.45
    licted
    -0.44
    ãĥ¯ãĥ³
    -0.42
    venth
    -0.42
    inki
    -0.41
    ogether
    -0.40
    POSITIVE LOGITS
    ,
    0.78
    ,...
    0.74
     we
    0.74
    ,.
    0.73
     they
    0.72
     there
    0.71
     it
    0.69
     he
    0.68
    ,,
    0.67
     she
    0.67
    Act Density 0.438%

    No Known Activations