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

    Neuronpedia

    INDEX
    Explanations

    phrases or verbs related to originating, starting, or causing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to origins or causes of events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icon
    -0.63
    avement
    -0.62
    anasia
    -0.62
    ebus
    -0.61
    secut
    -0.61
    aving
    -0.61
    ivable
    -0.61
    atur
    -0.60
    evaluate
    -0.59
    edo
    -0.59
    POSITIVE LOGITS
    actionDate
    0.91
    SourceFile
    0.80
    ĸļ
    0.80
    Orig
    0.75
     originating
    0.73
    REDACTED
    0.72
     nowhere
    0.72
     conduc
    0.72
    stay
    0.70
    ENCY
    0.70
    Act Density 0.059%

    No Known Activations