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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events involving personal risk or urgency

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate concern or fear for someone's safety or well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thanking
    -0.77
     ONLY
    -0.61
     Citation
    -0.60
     alot
    -0.60
     EVERY
    -0.57
     continuing
    -0.56
     summar
    -0.56
     THIS
    -0.56
     freaking
    -0.53
     referring
    -0.53
    POSITIVE LOGITS
    aband
    0.86
    sie
    0.79
    fit
    0.73
    effect
    0.73
    atches
    0.70
    ventures
    0.66
    ares
    0.65
    oots
    0.65
    luster
    0.64
    iously
    0.63
    Act Density 0.853%

    No Known Activations