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

    Neuronpedia

    INDEX
    Explanations

    references to addresses in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istic
    -0.18
    erty
    -0.17
    viz
    -0.16
    ä¿Ĺ
    -0.15
    ists
    -0.15
    opis
    -0.15
    iris
    -0.15
    ISTS
    -0.15
    jour
    -0.15
    isch
    -0.15
    POSITIVE LOGITS
    (es
    0.40
    ses
    0.31
    ess
    0.28
    able
    0.25
    sed
    0.24
    ible
    0.23
    sing
    0.22
    /es
    0.22
    esModule
    0.22
    er
    0.21
    Act Density 0.024%

    No Known Activations