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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by a verb in past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "he."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.64
    etheless
    -0.60
     pregn
    -0.58
     Veter
    -0.56
    urban
    -0.55
     cannabin
    -0.55
     Leban
    -0.55
     Composite
    -0.54
     Components
    -0.54
     Collective
    -0.54
    POSITIVE LOGITS
    zbollah
    1.16
     Majesty
    1.02
    eded
    0.99
    eding
    0.98
    resy
    0.98
    panic
    0.95
    ading
    0.93
    uristic
    0.88
    sych
    0.88
    avier
    0.88
    Act Density 0.278%

    No Known Activations