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

    Neuronpedia

    INDEX
    Explanations

    words related to information or allegations being revealed or coming to the public

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surfaced" and variations of it related to events coming to light

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.74
    jab
    -0.71
    alez
    -0.70
    atorial
    -0.70
    ierra
    -0.69
    rote
    -0.68
    shaw
    -0.67
    alien
    -0.67
    itar
    -0.66
    erie
    -0.66
    POSITIVE LOGITS
    tenance
    0.89
    GROUND
    0.79
    æ©
    0.70
     surfaced
    0.70
    FACE
    0.69
     Chrysler
    0.68
    pmwiki
    0.67
    ãĤ¨ãĥ«
    0.65
     BELOW
    0.65
    stals
    0.64
    Act Density 0.014%

    No Known Activations