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

    Neuronpedia

    INDEX
    Explanations

    financial numbers and percentages mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĹ
    -0.62
    ãģĻ
    -0.59
    hello
    -0.55
    "))
    -0.54
    POSE
    -0.51
    VIDEO
    -0.51
    ãĥ¡
    -0.50
    RO
    -0.49
     doping
    -0.49
    WATCH
    -0.49
    POSITIVE LOGITS
    sylv
    0.65
     analogous
    0.59
     meanwhile
    0.58
     similarly
    0.57
     modeled
    0.57
     likewise
    0.55
    SourceFile
    0.55
    erd
    0.55
    matic
    0.54
     pioneered
    0.53
    Act Density 2.313%

    No Known Activations