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

    Neuronpedia

    INDEX
    Explanations

    subject pronouns and their usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzle
    -0.18
     blind
    -0.15
    dict
    -0.15
    IDER
    -0.14
    çī§
    -0.14
    ucci
    -0.14
    herits
    -0.14
    æ½
    -0.14
    umph
    -0.14
    ajo
    -0.14
    POSITIVE LOGITS
    endon
    0.18
    eko
    0.17
    ek
    0.16
    eks
    0.16
    539
    0.15
    ripe
    0.15
     вов
    0.15
     pe
    0.14
    het
    0.14
    ripp
    0.14
    Act Density 0.016%

    No Known Activations