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

    Neuronpedia

    INDEX
    Explanations

    assertive statements or instructions with a somewhat forceful tone

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reliance or dependency on external factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Minor
    -0.77
    SPONSORED
    -0.75
    toggle
    -0.71
    SEE
    -0.67
    ivari
    -0.67
    Gender
    -0.67
    alter
    -0.66
    Includes
    -0.65
    Interview
    -0.64
    asses
    -0.63
    POSITIVE LOGITS
     Promise
    0.78
     promise
    0.77
     already
    0.76
     certainly
    0.75
     sooner
    0.73
    'll
    0.73
     surely
    0.72
     scams
    0.68
    ngth
    0.68
     otherwise
    0.66
    Act Density 0.458%

    No Known Activations