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

    Neuronpedia

    INDEX
    Explanations

    names or words related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of gambling or betting terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.95
     directions
    -0.68
     forth
    -0.65
     complaint
    -0.63
     Spiegel
    -0.62
    sbm
    -0.61
     capsule
    -0.60
    è»
    -0.59
     frontier
    -0.59
     complaints
    -0.59
    POSITIVE LOGITS
    lehem
    1.24
    culosis
    0.94
    nown
    0.88
    wana
    0.78
    olics
    0.75
    oola
    0.75
    rophe
    0.74
    emouth
    0.72
    antage
    0.72
    ت
    0.72
    Act Density 0.180%

    No Known Activations