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

    Neuronpedia

    INDEX
    Explanations

    instances of proof or evidence supporting a theory or assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritis
    -0.20
    ittest
    -0.20
     .|
    -0.15
    ÑĪÑĤ
    -0.15
    ynet
    -0.15
    оÑĥ
    -0.14
     Deniz
    -0.14
    åį
    -0.14
    icks
    -0.14
    itel
    -0.14
    POSITIVE LOGITS
    oph
    0.15
    flo
    0.15
    ng
    0.15
    alach
    0.14
     advanced
    0.14
    577
    0.14
     why
    0.14
     Cone
    0.14
    ży
    0.13
    커ìĬ¤
    0.13
    Act Density 0.252%

    No Known Activations