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

    Neuronpedia

    INDEX
    Explanations

    phrases related to weighing options or considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mony
    -0.15
    oleon
    -0.15
    \Php
    -0.15
    dney
    -0.15
    iban
    -0.15
    PLEX
    -0.15
    avra
    -0.15
    eng
    -0.14
    aptive
    -0.14
    avou
    -0.14
    POSITIVE LOGITS
    oriously
    0.15
    ÑĥлÑİ
    0.15
    ño
    0.15
    ädchen
    0.15
    braco
    0.14
    ôn
    0.14
     Rug
    0.14
     rim
    0.14
     Charm
    0.13
    EMU
    0.13
    Act Density 0.001%

    No Known Activations