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

    Neuronpedia

    INDEX
    Explanations

    plural nouns and their relationship to actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .WriteHeader
    -0.15
    erialize
    -0.15
    _ELEMENTS
    -0.14
    eated
    -0.14
    ãĥĥãĥĹ
    -0.14
    ridged
    -0.14
     Bilg
    -0.14
    ont
    -0.14
    _APPS
    -0.14
    itage
    -0.14
    POSITIVE LOGITS
    batch
    0.15
    ½æķ°
    0.15
    Batch
    0.15
    è´¨
    0.15
     batches
    0.15
    RICT
    0.14
     Benson
    0.14
    ubo
    0.14
    herits
    0.14
    blob
    0.14
    Act Density 0.006%

    No Known Activations