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

    Neuronpedia

    INDEX
    Explanations

    mentions of seasonal terms, specifically "winter" and "summer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inates
    -0.83
    otomy
    -0.80
    atem
    -0.78
    izabeth
    -0.77
    lesi
    -0.75
    ngth
    -0.74
    ional
    -0.73
    hered
    -0.72
    pez
    -0.71
    acters
    -0.70
    POSITIVE LOGITS
     Garden
    0.99
     Soldier
    0.98
    bottom
    0.96
     Veil
    0.96
     Festival
    0.95
     Olympics
    0.93
     Fever
    0.89
     Bout
    0.89
    bourne
    0.88
     Session
    0.87
    Act Density 0.034%

    No Known Activations