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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the provision of guidance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iros
    -0.17
    lish
    -0.16
     hoa
    -0.15
    lsa
    -0.15
    adin
    -0.15
     ç¿
    -0.14
    одаÑĢ
    -0.14
    OGLE
    -0.14
    GRES
    -0.14
    vem
    -0.13
    POSITIVE LOGITS
    xc
    0.15
     Bucc
    0.15
    ï¼Į以åıĬ
    0.15
     McL
    0.15
     tro
    0.15
     oraz
    0.15
    xbf
    0.14
    adera
    0.14
    ounc
    0.14
     Coron
    0.14
    Act Density 0.237%

    No Known Activations