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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to negative outcomes or situations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     velvet
    -0.82
     tele
    -0.80
     contingency
    -0.79
     crocod
    -0.78
     brid
    -0.77
     canv
    -0.77
     choking
    -0.76
     morph
    -0.75
     observable
    -0.75
     describ
    -0.75
    POSITIVE LOGITS
    Ļ
    1.30
    âĹı
    1.21
    æ©Ł
    1.18
    âĺ
    1.15
    [/
    1.14
    ©
    1.12
    §
    1.11
    Loading
    1.11
    Advertisements
    1.10
    ¨
    1.10
    Act Density 0.181%

    No Known Activations