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

    Neuronpedia

    INDEX
    Explanations

    phrases related to pretending or imaginative play

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pretend" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aird
    -0.71
    SET
    -0.68
    otype
    -0.64
    cedented
    -0.64
    ilings
    -0.63
    bid
    -0.62
    EStreamFrame
    -0.62
    asus
    -0.62
    atl
    -0.61
    è»
    -0.60
    POSITIVE LOGITS
     innocence
    1.05
     otherwise
    1.02
     ignorance
    0.93
     they
    0.81
     allegiance
    0.74
     THEY
    0.71
    ingly
    0.70
     he
    0.70
     nobody
    0.69
     nothing
    0.67
    Act Density 0.076%

    No Known Activations