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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences starting with the word "That."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "That."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SEE
    -0.79
    ģĸ
    -0.77
    ATURES
    -0.75
    Ĭ±
    -0.74
    ãĤ»
    -0.74
    ãĥīãĥ©
    -0.72
    IDES
    -0.71
    ciples
    -0.71
    IVERS
    -0.71
    paces
    -0.71
    POSITIVE LOGITS
     guy
    1.11
     happens
    1.04
     kind
    1.03
     ain
    1.03
     doesn
    0.99
     proves
    0.97
     undermines
    0.97
     bothers
    0.95
     sounds
    0.95
     wasn
    0.94
    Act Density 0.112%

    No Known Activations