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

    Neuronpedia

    INDEX
    Explanations

    references to public health (PH) indicators or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eff
    -0.18
    vice
    -0.15
    ean
    -0.14
     Vanity
    -0.14
     Cascade
    -0.14
     Daemon
    -0.13
     Ax
    -0.13
    F
    -0.13
    ój
    -0.13
    ieran
    -0.13
    POSITIVE LOGITS
    pear
    0.15
    ams
    0.14
    ruba
    0.14
     sil
    0.14
    oure
    0.13
    mel
    0.13
    Bindable
    0.13
     cái
    0.13
    reesome
    0.13
     nick
    0.13
    Act Density 0.025%

    No Known Activations