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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of shaping or influencing outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĻãĥ«
    -0.19
    erce
    -0.16
    ches
    -0.15
    esse
    -0.15
    eday
    -0.15
    mazon
    -0.14
    สาย
    -0.14
    bur
    -0.14
    ngr
    -0.14
    /pass
    -0.14
    POSITIVE LOGITS
    ToFit
    0.16
    ively
    0.16
    craft
    0.15
    olicit
    0.15
    -urlencoded
    0.15
    ulating
    0.15
    558
    0.15
    shape
    0.15
    (shape
    0.15
     shaped
    0.14
    Act Density 0.030%

    No Known Activations