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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating goals or aims

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating objectives or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Appears
    -0.69
     Torn
    -0.69
    faces
    -0.66
    hot
    -0.64
    note
    -0.63
     declarations
    -0.63
    guards
    -0.63
     Used
    -0.63
     Kop
    -0.61
     Lemon
    -0.61
    POSITIVE LOGITS
     maximize
    1.14
     conserve
    1.06
     emulate
    1.06
     stimulate
    1.05
     minimize
    1.04
     preserve
    1.04
     promote
    1.04
     provide
    1.03
     achieve
    1.01
     eliminate
    1.01
    Act Density 0.171%

    No Known Activations