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

    Neuronpedia

    INDEX
    Explanations

    words related to machinery or equipment

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "ators," indicating roles or functions in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ASED
    -0.71
    Print
    -0.63
     axle
    -0.62
     mountainous
    -0.61
     situational
    -0.61
     Earth
    -0.60
    OUT
    -0.60
     geological
    -0.59
     Ecology
    -0.59
     earth
    -0.59
    POSITIVE LOGITS
    hip
    1.44
    hips
    1.20
    ators
    1.14
    paces
    1.08
    ervatives
    0.97
    ":["
    0.93
    atives
    0.92
    poons
    0.92
    etter
    0.88
    */(
    0.87
    Act Density 0.026%

    No Known Activations