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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences emphasizing the presence or visibility of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert the clarity or obviousness of a situation or fact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.75
    atern
    -0.74
    fing
    -0.71
    pton
    -0.70
    create
    -0.69
    king
    -0.67
    pered
    -0.67
    att
    -0.66
    scribe
    -0.66
    EStreamFrame
    -0.66
    POSITIVE LOGITS
    iary
    1.33
     evident
    1.02
    ieth
    0.83
    ãĥ³
    0.81
    ãĥ¼ãĥĨ
    0.81
    ãĤ¦ãĤ¹
    0.80
    icity
    0.79
    ial
    0.78
    ãĥĭ
    0.77
    éĹ
    0.76
    Act Density 0.005%

    No Known Activations