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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating responsibility and accountability

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" frequently

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.77
    ovember
    -0.70
    ĸļ
    -0.68
     lapt
    -0.65
    ober
    -0.65
     Presence
    -0.63
     unfocusedRange
    -0.62
    assium
    -0.61
    berus
    -0.60
     agre
    -0.60
    POSITIVE LOGITS
     those
    0.76
    those
    0.73
    pees
    0.72
     these
    0.71
     respondents
    0.70
     us
    0.69
     thousands
    0.69
     reasons
    0.66
     whom
    0.65
     applicants
    0.64
    Act Density 0.085%

    No Known Activations