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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" indicating intention or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kil
    -0.16
    stead
    -0.15
    /we
    -0.14
    ragen
    -0.14
    fillType
    -0.14
    abilia
    -0.14
    sticks
    -0.13
    mium
    -0.13
    midt
    -0.13
    zelf
    -0.13
    POSITIVE LOGITS
    gether
    0.28
    /from
    0.26
    plevel
    0.25
    ogle
    0.20
    ledo
    0.19
    /about
    0.19
    pline
    0.17
    asting
    0.16
    iling
    0.16
    tem
    0.16
    Act Density 0.892%

    No Known Activations