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

    Neuronpedia

    INDEX
    Explanations

    phrases related to longing or desire for something

    oai_token-act-pair · gpt-3.5-turbo

    verbs and expressions indicating a desire or inclination towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mt
    -0.73
    agar
    -0.70
    checks
    -0.67
    reported
    -0.65
    authorized
    -0.65
    SPONSORED
    -0.65
    documented
    -0.64
    arson
    -0.63
    mask
    -0.63
    upper
    -0.62
    POSITIVE LOGITS
     revenge
    0.90
     conserve
    0.85
     renewal
    0.76
     reward
    0.74
     fulfilled
    0.71
     patience
    0.69
     desperately
    0.68
     vengeance
    0.68
     fulfil
    0.67
     perfection
    0.67
    Act Density 0.371%

    No Known Activations