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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names related to a certain context or category

    oai_token-act-pair · gpt-3.5-turbo

    names and locations related to specific events or persons, particularly focusing on the term "Tav"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    head
    -0.84
    ŃĶ
    -0.74
    phrine
    -0.73
     autopsy
    -0.73
    omial
    -0.73
     Laden
    -0.71
    dose
    -0.69
    undai
    -0.67
    hood
    -0.64
    ACTED
    -0.62
    POSITIVE LOGITS
    liga
    0.85
    lain
    0.80
    ernels
    0.79
    ues
    0.78
    HAEL
    0.76
    ittal
    0.75
     Uriel
    0.75
    irtual
    0.74
    ï¸ı
    0.73
     comprom
    0.73
    Act Density 0.038%

    No Known Activations