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

    Neuronpedia

    INDEX
    Explanations

    phrases related to coercion or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve coercion or manipulation towards a desired outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.71
    hop
    -0.64
     corpus
    -0.62
    entimes
    -0.61
    ghai
    -0.61
     capacitor
    -0.60
     headphone
    -0.59
    zai
    -0.59
     paced
    -0.58
     slowdown
    -0.57
    POSITIVE LOGITS
     adulthood
    1.03
    veyard
    0.82
    jected
    0.70
    qqa
    0.70
     orbit
    0.69
     ob
    0.68
     submission
    0.68
    pload
    0.67
    wards
    0.66
    jection
    0.66
    Act Density 0.079%

    No Known Activations