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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that express relationships or evaluations between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    757
    -0.16
    atchet
    -0.15
    romo
    -0.15
    ARRANT
    -0.15
     instead
    -0.15
    rupa
    -0.15
    ToPoint
    -0.14
    jun
    -0.14
    /operator
    -0.14
    renom
    -0.14
    POSITIVE LOGITS
     mere
    0.19
     any
    0.17
    ervo
    0.16
     Ø£ÙĬ
    0.16
    any
    0.15
    ëŀ¨
    0.15
    èĮĥ
    0.15
    ÑĢеÑģ
    0.15
    ä»»ä½ķ
    0.14
    aler
    0.14
    Act Density 0.159%

    No Known Activations