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

    Neuronpedia

    INDEX
    Explanations

    - different entities or entities interacting with each other

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lance
    -0.55
    lus
    -0.52
    lov
    -0.52
     Indust
    -0.52
    indust
    -0.52
    asta
    -0.51
    LER
    -0.50
    vich
    -0.50
    undown
    -0.49
    gow
    -0.48
    POSITIVE LOGITS
    fold
    0.80
     hundred
    0.78
     thousand
    0.78
     dimensional
    0.78
     dozen
    0.73
     consecutive
    0.73
     thirds
    0.73
     pairs
    0.73
     feet
    0.73
    teen
    0.71
    Act Density 14.029%

    No Known Activations