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

    Neuronpedia

    INDEX
    Explanations

    phrases related to escalators or upward movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.15
     Morrow
    -0.15
    ÑĹ
    -0.15
    Norm
    -0.14
    å¼¥
    -0.14
    Cons
    -0.14
    ''"
    -0.14
    SKI
    -0.13
     Glob
    -0.13
    iron
    -0.13
    POSITIVE LOGITS
    atoi
    0.15
    .Magenta
    0.15
    lint
    0.14
    ruz
    0.14
    enty
    0.14
    etty
    0.13
    iband
    0.13
    Ń
    0.13
    sip
    0.13
    anya
    0.13
    Act Density 0.000%

    No Known Activations