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

    Neuronpedia

    INDEX
    Explanations

    phrases focused on evaluating rules, concepts, and distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufs
    -0.17
     wonder
    -0.15
     fore
    -0.14
    izr
    -0.14
    /xhtml
    -0.14
    stoup
    -0.14
    žel
    -0.14
    FS
    -0.14
     sorte
    -0.14
    enson
    -0.13
    POSITIVE LOGITS
     versus
    0.26
     vs
    0.25
    -vs
    0.19
     vice
    0.18
     Vs
    0.17
    /how
    0.16
    _vs
    0.16
    /non
    0.16
    /not
    0.15
    имÑĥ
    0.14
    Act Density 0.103%

    No Known Activations