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

    Neuronpedia

    INDEX
    Explanations

    terms related to size and ranking in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spark
    -0.15
    nah
    -0.15
    lang
    -0.15
    hora
    -0.14
    eft
    -0.14
    lege
    -0.14
    Plus
    -0.13
    itler
    -0.13
     Zus
    -0.13
    agos
    -0.13
    POSITIVE LOGITS
     followed
    0.43
     behind
    0.37
     ahead
    0.31
    follow
    0.31
     Behind
    0.28
     according
    0.27
     overall
    0.27
    ahead
    0.26
    Behind
    0.25
    according
    0.25
    Act Density 0.124%

    No Known Activations