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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific name ("compatriots") followed by some activity or description

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with compatibility and notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GH
    -0.70
    HCR
    -0.70
    OOD
    -0.67
    mith
    -0.67
    wyn
    -0.66
    kel
    -0.65
     unlocking
    -0.62
    GE
    -0.61
     downhill
    -0.60
    GL
    -0.60
    POSITIVE LOGITS
    riot
    1.05
    orical
    1.03
    ional
    1.01
    orial
    0.99
    riots
    0.97
    orship
    0.95
    orically
    0.93
    ancies
    0.92
    ories
    0.89
    ability
    0.88
    Act Density 0.053%

    No Known Activations