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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģªãģĮ
    -0.17
    aggio
    -0.16
    _ASSUME
    -0.15
    empo
    -0.15
    airo
    -0.14
    omu
    -0.14
    icide
    -0.14
    ublic
    -0.14
    ilio
    -0.14
    ACHI
    -0.13
    POSITIVE LOGITS
    çı¾
    0.15
     div
    0.14
     mean
    0.14
     æ¾
    0.14
    emale
    0.13
    riv
    0.13
    они
    0.13
    çİ°
    0.13
    memcpy
    0.12
     sovereignty
    0.12
    Act Density 0.111%

    No Known Activations