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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that signify emotional expressions or storytelling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STALL
    -0.16
    quito
    -0.15
    izzy
    -0.15
    ìŀ
    -0.14
    typings
    -0.14
    MAND
    -0.14
    ança
    -0.14
    utin
    -0.13
    TTY
    -0.13
    alion
    -0.13
    POSITIVE LOGITS
     also
    0.28
     Also
    0.26
    also
    0.25
    Also
    0.25
     Secondly
    0.21
     ALSO
    0.20
     ÑĤакже
    0.19
     otherwise
    0.19
     también
    0.19
     juga
    0.19
    Act Density 0.257%

    No Known Activations