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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "where"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bullock
    -0.80
     Betts
    -0.79
     initData
    -0.73
     Vance
    -0.72
    ApiModelProperty
    -0.69
    t
    -0.67
    Evelyn
    -0.66
    コール
    -0.65
     Huff
    -0.65
     sklearn
    -0.62
    POSITIVE LOGITS
     where
    1.80
    Where
    1.79
     Where
    1.79
     WHERE
    1.76
    where
    1.74
    WHERE
    1.65
     Où
    1.60
    Donde
    1.40
     Onde
    1.40
     Donde
    1.33
    Act Density 0.095%

    No Known Activations