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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to political terms, such as "plebiscite" and "political solution"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'b' and words denoting actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.80
    owered
    -0.79
    kefeller
    -0.75
    externalActionCode
    -0.75
    eeper
    -0.73
     Aden
    -0.71
    terson
    -0.68
    orno
    -0.68
     sleeper
    -0.67
     Morty
    -0.66
    POSITIVE LOGITS
    ï¸
    0.72
    itely
    0.68
    mentioned
    0.67
    ×ij
    0.67
    ×Ļ
    0.64
    fty
    0.63
    ׾
    0.63
    ×ķ
    0.63
    Say
    0.63
    Dash
    0.63
    Act Density 0.183%

    No Known Activations