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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or doubt

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of the word "really" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifully
    -0.79
     nevertheless
    -0.79
    vic
    -0.76
    tein
    -0.76
     nonetheless
    -0.75
    moil
    -0.70
    iful
    -0.67
    enary
    -0.66
    VL
    -0.64
    ItemThumbnailImage
    -0.63
    POSITIVE LOGITS
     cared
    0.97
     bothered
    0.94
     mattered
    0.90
     bother
    0.82
     fit
    0.76
     understood
    0.75
    hin
    0.74
     bothering
    0.74
    FTWARE
    0.73
     anything
    0.71
    Act Density 0.056%

    No Known Activations