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

    Neuronpedia

    INDEX
    Explanations

    words related to announcing or signaling significant events or changes

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to heralding or proclaiming significant events or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RF
    -0.69
     compromising
    -0.69
    thia
    -0.65
     interfering
    -0.65
     probing
    -0.65
     digging
    -0.63
    pn
    -0.62
     dstg
    -0.61
    ascript
    -0.61
     sqor
    -0.60
    POSITIVE LOGITS
     virtues
    0.85
     triumphant
    0.85
     victory
    0.81
     feats
    0.79
    agne
    0.79
     savior
    0.78
     successes
    0.78
     goodbye
    0.74
     victories
    0.74
     achievements
    0.74
    Act Density 0.158%

    No Known Activations