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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant names in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Nested
    -0.16
    nested
    -0.16
    cales
    -0.15
     nested
    -0.14
    unks
    -0.14
    _nested
    -0.14
    θο
    -0.14
    yz
    -0.14
    zf
    -0.14
    irable
    -0.14
    POSITIVE LOGITS
    ahlen
    0.17
    312
    0.15
    åĩ¡
    0.15
     Шев
    0.14
    ml
    0.13
    illing
    0.13
    rus
    0.13
     uncert
    0.13
     Joan
    0.13
    encer
    0.13
    Act Density 0.005%

    No Known Activations