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

    Neuronpedia

    INDEX
    Explanations

    occurrences of words related to societal issues or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampo
    -0.15
    oren
    -0.15
    ATUS
    -0.15
    avicon
    -0.14
    .called
    -0.14
     Humph
    -0.14
    ContentLoaded
    -0.14
    ä¿Ĭ
    -0.14
    .Counter
    -0.13
    .agent
    -0.13
    POSITIVE LOGITS
    ita
    0.17
    arges
    0.16
    zeÅĪ
    0.15
    Keeper
    0.14
    wald
    0.14
    oke
    0.14
    pare
    0.14
    Malloc
    0.13
    it
    0.13
    ymph
    0.13
    Act Density 0.001%

    No Known Activations