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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promotions and appointments in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.69
     Brill
    -0.66
     magnification
    -0.64
     defic
    -0.61
     Brut
    -0.59
    unts
    -0.58
    geries
    -0.57
     NK
    -0.56
     coh
    -0.56
     reflections
    -0.55
    POSITIVE LOGITS
    inary
    0.62
    aquin
    0.62
    ache
    0.60
    Synopsis
    0.59
    abeth
    0.59
    inem
    0.58
    Movie
    0.56
    prison
    0.56
    ijah
    0.54
    Streamer
    0.54
    Act Density 0.065%

    No Known Activations