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

    Neuronpedia

    INDEX
    Explanations

    uses of the word "all" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to comprehensive or universal policies and actions affecting a wide range of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    potion
    -0.81
    fman
    -0.66
    IDS
    -0.65
    ritic
    -0.65
    bal
    -0.63
    aminer
    -0.63
    assembly
    -0.62
    FH
    -0.62
     tremend
    -0.61
    zn
    -0.61
    POSITIVE LOGITS
    ocating
    1.29
     kinds
    1.21
     sorts
    1.16
    iances
    1.06
    igators
    1.05
    owing
    1.02
    usions
    0.96
     manner
    0.96
    igator
    0.95
    iance
    0.94
    Act Density 0.123%

    No Known Activations