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

    Neuronpedia

    INDEX
    Explanations

    common words related to problems, considerations, and concerns

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to issues or concerns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Õ
    -0.73
    SN
    -0.72
    oning
    -0.71
    INAL
    -0.69
    yss
    -0.68
    ãĤ¨ãĥ«
    -0.68
    otide
    -0.68
    PATH
    -0.67
    thumbnails
    -0.66
    Vel
    -0.65
    POSITIVE LOGITS
    paces
    0.97
    heet
    0.96
    pace
    0.94
    chool
    0.93
    afe
    0.90
     abound
    0.90
    hops
    0.89
    hooting
    0.88
    pring
    0.88
    hips
    0.84
    Act Density 0.395%

    No Known Activations