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

    Neuronpedia

    INDEX
    Explanations

    words related to weights in kilograms

    oai_token-act-pair · gpt-3.5-turbo

    references to weight measurements in kilograms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Snapchat
    -0.67
     Dee
    -0.65
     BET
    -0.64
    gotten
    -0.63
    GROUND
    -0.63
    EEE
    -0.60
    structed
    -0.60
     Acad
    -0.59
     Frontier
    -0.59
    protected
    -0.59
    POSITIVE LOGITS
    kg
    0.95
    atsu
    0.88
    enger
    0.84
     kg
    0.81
    ingly
    0.80
    etsu
    0.78
    ostic
    0.78
    eto
    0.77
    rieg
    0.77
    JV
    0.77
    Act Density 0.006%

    No Known Activations