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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and dashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oth
    -0.18
    hl
    -0.15
    pei
    -0.14
    COPY
    -0.14
    åīĩ
    -0.14
    arken
    -0.14
    incerely
    -0.14
    .metro
    -0.14
    Specifier
    -0.14
    ا
    -0.13
    POSITIVE LOGITS
     and
    0.18
     but
    0.18
     or
    0.18
    amil
    0.16
     plus
    0.16
     hence
    0.15
    _INITIALIZER
    0.15
    ãĤĵãģ¨
    0.15
     except
    0.14
     ç¿
    0.14
    Act Density 0.106%

    No Known Activations