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

    Neuronpedia

    INDEX
    Explanations

    phrases related to filtering or reducing options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lech
    -0.15
    365
    -0.15
    æĮ
    -0.14
    afs
    -0.14
    aging
    -0.14
    hari
    -0.14
    ihat
    -0.14
     Spiel
    -0.13
    robat
    -0.13
     aging
    -0.13
    POSITIVE LOGITS
    odzi
    0.15
    aters
    0.14
     Manson
    0.14
    èĤ¡ä»½
    0.14
    erea
    0.14
    ely
    0.14
     Sanity
    0.14
    meteor
    0.14
    rlen
    0.14
    _queryset
    0.14
    Act Density 0.182%

    No Known Activations