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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "step" and its variations in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lid
    -0.17
    Äįet
    -0.16
    ุà¸Ķ
    -0.16
    uges
    -0.15
    lig
    -0.15
    er
    -0.15
    stüt
    -0.15
    park
    -0.15
    olk
    -0.15
    estar
    -0.14
    POSITIVE LOGITS
    wise
    0.24
    éª
    0.24
    -by
    0.22
    enson
    0.22
    han
    0.21
    pe
    0.21
    dad
    0.20
    pling
    0.19
    mother
    0.19
    hen
    0.18
    Act Density 0.026%

    No Known Activations