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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate things being regarded or designated in a certain way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olin
    -0.17
    apper
    -0.14
    ãģ£ãģį
    -0.14
    doch
    -0.14
    gle
    -0.14
    abwe
    -0.14
    _serv
    -0.13
    _deinit
    -0.13
    ominator
    -0.13
    ÃŃky
    -0.13
    POSITIVE LOGITS
     to
    0.22
    ately
    0.16
    orges
    0.16
    hof
    0.15
    /request
    0.15
     having
    0.15
     sebagai
    0.15
     part
    0.15
     sac
    0.14
     separately
    0.14
    Act Density 0.052%

    No Known Activations