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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a mission or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¡ļ
    -0.14
    祥
    -0.14
    esus
    -0.14
    hei
    -0.14
    isu
    -0.14
    боÑĢа
    -0.14
    em
    -0.13
    ertas
    -0.13
     Symbol
    -0.13
    á»Ļ
    -0.13
    POSITIVE LOGITS
     tall
    0.19
    ocker
    0.18
     fair
    0.17
    -ok
    0.16
    cÃŃ
    0.16
    IDGE
    0.15
     underst
    0.15
     sure
    0.15
     indication
    0.15
     valid
    0.15
    Act Density 0.113%

    No Known Activations