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

    Neuronpedia

    INDEX
    Explanations

    phrases related to extreme situations, such as crises and record occurrences

    oai_token-act-pair · gpt-3.5-turbo

    indications of significant events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç·
    -0.67
    ãĥīãĥ©
    -0.67
    DE
    -0.65
    ãĥĥ
    -0.60
    kas
    -0.60
    èĪ
    -0.60
    Kevin
    -0.59
    jon
    -0.59
    kowski
    -0.59
    00200000
    -0.58
    POSITIVE LOGITS
     EVER
    1.54
     ever
    1.50
    ever
    1.37
     imaginable
    1.35
     Ever
    1.12
     anywhere
    1.07
    Ever
    0.99
     conceivable
    0.81
     possible
    0.76
     feas
    0.73
    Act Density 0.824%

    No Known Activations