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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ena
    -0.16
    inent
    -0.16
    linger
    -0.15
    _CONSTANT
    -0.15
    amment
    -0.15
    æĴ®
    -0.14
    abil
    -0.14
    ument
    -0.14
    fic
    -0.14
    ké
    -0.14
    POSITIVE LOGITS
    諾
    0.14
    BUR
    0.14
     Kho
    0.13
    ATTER
    0.13
    ocrates
    0.13
    atica
    0.12
    icans
    0.12
    atcher
    0.12
     hitch
    0.12
     sem
    0.12
    Act Density 0.001%

    No Known Activations