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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to having control or power over a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Shot
    -0.78
    ©¶æ¥µ
    -0.78
    Incre
    -0.71
     Called
    -0.70
    Switch
    -0.70
    Down
    -0.69
    Rocket
    -0.67
    Tier
    -0.64
    JM
    -0.63
    Points
    -0.62
    POSITIVE LOGITS
    rican
    0.72
     ______
    0.71
     rapes
    0.69
     oneself
    0.68
     isolation
    0.66
     fiat
    0.65
     extortion
    0.65
     funer
    0.64
    merce
    0.64
    bernatorial
    0.64
    Act Density 0.550%

    No Known Activations