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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ils
    -0.15
    ista
    -0.15
    idth
    -0.15
    sexual
    -0.15
    road
    -0.15
    ItemType
    -0.14
    line
    -0.14
     behalf
    -0.14
    iyet
    -0.14
    Item
    -0.13
    POSITIVE LOGITS
    /lo
    0.22
    /dis
    0.21
    ably
    0.19
    -minded
    0.18
    able
    0.18
     Ike
    0.15
    elihood
    0.15
    WISE
    0.15
    ewise
    0.14
    how
    0.14
    Act Density 0.047%

    No Known Activations