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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Oh" used repeatedly in various expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.91
     guiActiveUn
    -0.81
    İĭ
    -0.76
    inction
    -0.74
    ļéĨĴ
    -0.73
    resso
    -0.71
    UGC
    -0.69
    pec
    -0.69
    velop
    -0.68
    MRI
    -0.67
    POSITIVE LOGITS
     yeah
    1.15
     yes
    0.99
     sorry
    0.97
     sir
    0.89
     please
    0.89
     dear
    0.87
     uh
    0.84
     thank
    0.83
     maybe
    0.83
     um
    0.81
    Act Density 0.073%

    No Known Activations