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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questioning or expressing uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    repeating characters or special symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.78
     Mayo
    -0.74
     snail
    -0.74
     Lou
    -0.73
     Isle
    -0.72
     Ler
    -0.70
     Lerner
    -0.69
     stri
    -0.69
     Lem
    -0.68
     Nanto
    -0.68
    POSITIVE LOGITS
    Ŀ
    1.84
    ¡
    1.37
    °
    1.36
    ¦
    1.23
    §
    1.23
    ŀ
    1.21
    ©
    1.21
    ª
    1.17
    ´
    1.17
    ī
    1.16
    Act Density 0.195%

    No Known Activations