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

    Neuronpedia

    INDEX
    Explanations

    words related to public speaking or interviews

    oai_token-act-pair · gpt-3.5-turbo

    instances of formal speech or references to speaking engagements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     documented
    -0.69
     needles
    -0.68
     proven
    -0.67
    usercontent
    -0.67
     maple
    -0.66
     violates
    -0.61
     someday
    -0.61
     Entered
    -0.60
     gravy
    -0.60
     thri
    -0.59
    POSITIVE LOGITS
     Collider
    0.89
     HuffPost
    0.78
    éĹ
    0.76
    raltar
    0.75
     keynote
    0.74
     commencement
    0.74
     midday
    0.74
     podium
    0.73
     POLITICO
    0.72
     behalf
    0.72
    Act Density 0.282%

    No Known Activations