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

    Neuronpedia

    INDEX
    Explanations

    words related to warnings and alerts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to analysis and insights, particularly in a questioning or investigative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouver
    -0.72
    aux
    -0.67
     docks
    -0.65
     kin
    -0.64
     contiguous
    -0.63
     quart
    -0.63
     halls
    -0.62
     pounds
    -0.61
     exhibits
    -0.61
     cart
    -0.60
    POSITIVE LOGITS
    ingly
    0.81
    inducing
    0.76
    ustration
    0.74
    oggle
    0.73
    terday
    0.71
    hift
    0.71
     worrying
    0.71
    faced
    0.69
    bh
    0.68
    ably
    0.67
    Act Density 0.252%

    No Known Activations