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

    Neuronpedia

    INDEX
    Explanations

    contractions and negative phrases, particularly relating to uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     insuffisamment
    -0.40
     pungkasnya
    -0.39
     also
    -0.38
     rồi
    -0.37
    also
    -0.37
    Basta
    -0.34
     Heywood
    -0.34
    enumi
    -0.34
     Sz
    -0.33
     saha
    -0.33
    POSITIVE LOGITS
     bother
    0.77
     even
    0.75
     bothered
    0.75
     siquiera
    0.75
     bothering
    0.74
     notice
    0.73
     noticing
    0.72
     ever
    0.71
     cared
    0.70
     consciously
    0.70
    Act Density 0.454%

    No Known Activations