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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "he" followed by a verb in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.73
    etheless
    -0.63
    emale
    -0.61
     Leban
    -0.58
    igmatic
    -0.56
    aura
    -0.55
    requisite
    -0.54
    Category
    -0.53
    Temperature
    -0.53
     pregn
    -0.53
    POSITIVE LOGITS
    zbollah
    1.07
    mos
    0.89
    sych
    0.81
    resy
    0.79
     Majesty
    0.79
    eded
    0.79
    aven
    0.77
    idi
    0.76
    gemony
    0.76
    uristic
    0.74
    Act Density 0.207%

    No Known Activations