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

    Neuronpedia

    INDEX
    Explanations

    phrases or references to identity, relationships, and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oundingBox
    -0.16
    .synthetic
    -0.16
    ëĭ¹
    -0.15
    оÑĢи
    -0.15
    liž
    -0.14
    amarin
    -0.14
    ify
    -0.14
    γον
    -0.13
    zyst
    -0.13
    acing
    -0.13
    POSITIVE LOGITS
    paragus
    0.15
    ril
    0.15
    idth
    0.15
     cob
    0.15
    obo
    0.15
    ITH
    0.14
    uka
    0.14
    óc
    0.14
    rophy
    0.14
    /flutter
    0.13
    Act Density 0.251%

    No Known Activations