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

    Neuronpedia

    INDEX
    Explanations

    phrases related to endorsement or approval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to horses and equestrian themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -0.69
    rylic
    -0.64
     subconscious
    -0.62
    ellar
    -0.62
    aleigh
    -0.62
    aeper
    -0.61
     meticulously
    -0.60
    DERR
    -0.60
     unintentionally
    -0.59
     session
    -0.59
    POSITIVE LOGITS
    ments
    1.01
    lihood
    0.99
    orse
    0.90
    manship
    0.86
    MENTS
    0.82
     Reincarn
    0.80
    ances
    0.78
    à¤
    0.77
    weight
    0.77
    ãĥĨ
    0.75
    Act Density 0.006%

    No Known Activations