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

    Neuronpedia

    INDEX
    Explanations

    words related to societal issues and policies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "like," indicating comparisons or examples related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.79
    ells
    -0.79
    essing
    -0.78
    arbon
    -0.77
    enary
    -0.76
    atched
    -0.73
    essed
    -0.72
    acia
    -0.72
    inion
    -0.71
    ennes
    -0.71
    POSITIVE LOGITS
    lihood
    1.31
    lier
    0.97
     ours
    0.94
    liest
    0.87
     hers
    0.78
     yours
    0.75
    minded
    0.72
    liness
    0.69
     minded
    0.68
    åĭ
    0.67
    Act Density 0.068%

    No Known Activations