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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize significant events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xit
    -1.01
    raped
    -0.79
     ILCS
    -0.69
    via
    -0.68
    cheat
    -0.67
    ritch
    -0.66
    apons
    -0.64
    amber
    -0.63
    tein
    -0.63
    hibited
    -0.62
    POSITIVE LOGITS
     contender
    0.91
     (>
    0.68
     coincidence
    0.68
     Bust
    0.66
     difference
    0.65
     misconception
    0.65
     hitters
    0.64
     understatement
    0.63
     happening
    0.63
    Sense
    0.62
    Act Density 0.080%

    No Known Activations