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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an invitation for interaction or feedback

    oai_token-act-pair · gpt-3.5-turbo

    expressions of encouragement or invitation to engage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     notch
    -0.70
     PBS
    -0.67
     Bastard
    -0.66
     Parenthood
    -0.63
     Mub
    -0.63
     misc
    -0.61
     Boko
    -0.59
    netflix
    -0.58
     Mun
    -0.57
     Lup
    -0.57
    POSITIVE LOGITS
    INGS
    0.79
    ings
    0.79
     compelled
    0.78
    ername
    0.78
     comfortable
    0.75
    good
    0.75
    eline
    0.73
     free
    0.73
    pee
    0.72
    iven
    0.72
    Act Density 0.043%

    No Known Activations