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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific research or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailability
    -0.16
     Victor
    -0.16
    Vict
    -0.15
    nonnull
    -0.15
    ainless
    -0.15
     Vic
    -0.15
    urally
    -0.15
    ارج
    -0.15
    ÃŃky
    -0.15
    iosis
    -0.14
    POSITIVE LOGITS
    ative
    0.81
    ATIVE
    0.68
    atives
    0.64
    atively
    0.59
    itive
    0.59
    ativ
    0.58
    аÑĤив
    0.57
    ativa
    0.54
    ativo
    0.53
    ativas
    0.47
    Act Density 0.095%

    No Known Activations