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

    Neuronpedia

    INDEX
    Explanations

    references to cause-and-effect relationships or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambre
    -0.16
    wick
    -0.15
    ento
    -0.15
    olon
    -0.14
    entine
    -0.14
    ignty
    -0.14
    anz
    -0.14
    ög
    -0.13
    ven
    -0.13
    rang
    -0.13
    POSITIVE LOGITS
    erset
    0.17
    ingly
    0.15
    ushman
    0.14
    åħ·
    0.14
     linkage
    0.14
    avenport
    0.14
    forth
    0.14
    Ïĩε
    0.14
    iverse
    0.14
    InputDialog
    0.14
    Act Density 0.014%

    No Known Activations