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

    Neuronpedia

    INDEX
    Explanations

    elements related to accessibility and inclusivity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leet
    -0.15
     etc
    -0.15
    itat
    -0.15
    etc
    -0.15
    eph
    -0.14
     reserved
    -0.14
    stå
    -0.14
    ulent
    -0.13
    -pro
    -0.13
    ion
    -0.13
    POSITIVE LOGITS
     anywhere
    0.18
     ANY
    0.17
    679
    0.17
    latable
    0.17
    ách
    0.16
     irgend
    0.15
    uento
    0.15
    podob
    0.15
    .soft
    0.14
     anybody
    0.14
    Act Density 0.154%

    No Known Activations