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

    Neuronpedia

    INDEX
    Explanations

    patterns of cause and effect in descriptions of events or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avit
    -0.16
    ago
    -0.15
    exampleInputEmail
    -0.15
    akh
    -0.14
    ulum
    -0.14
    ulus
    -0.14
    inet
    -0.14
    ç¬
    -0.14
    aks
    -0.13
    jec
    -0.13
    POSITIVE LOGITS
     its
    0.19
    orex
    0.17
     revis
    0.15
    åħ¶
    0.15
    åĩ
    0.14
     Its
    0.14
     prem
    0.14
    79
    0.14
    its
    0.14
     Klo
    0.14
    Act Density 0.140%

    No Known Activations