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

    Neuronpedia

    INDEX
    Explanations

    numerical data points or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to voting or election results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.87
    istor
    -0.68
     NEVER
    -0.64
     subsequ
    -0.57
     Canaver
    -0.55
    Reviewer
    -0.55
     "$:/
    -0.54
    liquid
    -0.54
    zos
    -0.53
     conditioned
    -0.53
    POSITIVE LOGITS
     apiece
    1.35
    %.
    1.07
    .
    0.90
    +.
    0.86
    %;
    0.84
     respectively
    0.80
    .;
    0.79
    ;
    0.78
    %,
    0.77
    *.
    0.76
    Act Density 0.296%

    No Known Activations