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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to standing out or distinguishing oneself in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ando
    -0.15
    æĤŁ
    -0.15
    to
    -0.15
    icus
    -0.15
    ato
    -0.14
    tober
    -0.14
    idon
    -0.14
     Bucc
    -0.14
    ion
    -0.13
     close
    -0.13
    POSITIVE LOGITS
     above
    0.26
     ABOVE
    0.23
    above
    0.23
     ÑģÑĢеди
    0.21
     amongst
    0.21
     among
    0.19
     Above
    0.19
    Above
    0.18
    以ä¸Ĭ
    0.18
    among
    0.18
    Act Density 0.032%

    No Known Activations