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

    Neuronpedia

    INDEX
    Explanations

    terms related to variability and differences in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eca
    -0.15
    оÑģоб
    -0.15
    anner
    -0.15
    uckets
    -0.14
    ANNER
    -0.14
    idine
    -0.14
    ilian
    -0.14
    .rs
    -0.14
    onian
    -0.14
    ymbols
    -0.14
    POSITIVE LOGITS
     depending
    0.24
     degrees
    0.22
    degrees
    0.22
    depending
    0.19
    ingly
    0.19
    mad
    0.19
    iable
    0.17
    avi
    0.17
     Degrees
    0.17
     mad
    0.16
    Act Density 0.032%

    No Known Activations