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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions and statements

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated lists or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.81
    ,...
    -0.75
    """
    -0.71
    SourceFile
    -0.71
    -
    -0.68
    !,
    -0.68
    vale
    -0.68
    Previous
    -0.67
    Wire
    -0.67
    Actor
    -0.67
    POSITIVE LOGITS
     somew
    0.69
     diminishing
    0.57
     rudimentary
    0.56
    stellar
    0.55
     tacit
    0.54
     nonexistent
    0.54
     incomplete
    0.53
    utenberg
    0.53
    ifiable
    0.52
     criminally
    0.52
    Act Density 0.124%

    No Known Activations