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

    Neuronpedia

    INDEX
    Explanations

    statements or declarations made by individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to official statements or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     irrad
    -0.74
    _>
    -0.73
     unsus
    -0.68
     underestimated
    -0.63
    odynam
    -0.61
     fertile
    -0.59
     Enemy
    -0.58
    iencies
    -0.58
     nerv
    -0.57
     fantasies
    -0.57
    POSITIVE LOGITS
     thanking
    0.81
     announcing
    0.75
    irming
    0.75
     apologizing
    0.74
    terday
    0.73
    obo
    0.73
     statement
    0.71
     behalf
    0.70
     spokesperson
    0.70
     acknowledging
    0.67
    Act Density 0.264%

    No Known Activations