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

    Neuronpedia

    INDEX
    Explanations

    sequences of dashes or hyphens used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.18
    'll
    -0.18
    'm
    -0.16
    're
    -0.16
     --
    -0.15
    -----
    -0.15
    'em
    -0.15
    'y
    -0.15
    ï¼ļ"
    -0.15
    'n
    -0.15
    POSITIVE LOGITS
    ––
    0.27
    –
    0.22
    /+
    0.21
    >
    0.19
     “
    0.19
    /-
    0.18
    er
    0.17
    ————————
    0.17
    ————————————————
    0.17
     (“
    0.16
    Act Density 0.103%

    No Known Activations