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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to" followed by numerical values or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    p
    -0.17
    rl
    -0.15
    emp
    -0.15
    t
    -0.14
    h
    -0.14
    m
    -0.14
    /OR
    -0.14
    aylor
    -0.14
    j
    -0.14
    ij
    -0.14
    POSITIVE LOGITS
    leine
    0.17
    radient
    0.17
    Ñģклад
    0.17
    okino
    0.16
    skill
    0.15
    Unnamed
    0.15
    ehir
    0.15
    .gstatic
    0.15
    >null
    0.15
     noreferrer
    0.15
    Act Density 0.031%

    No Known Activations