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

    Neuronpedia

    INDEX
    Explanations

    phrases or contexts related to conditional or preferential statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.16
    igraph
    -0.15
     rằng
    -0.14
    agu
    -0.14
    adil
    -0.13
    them
    -0.13
     whereas
    -0.13
    uel
    -0.13
     ведÑĮ
    -0.13
     наÑĢ
    -0.13
    POSITIVE LOGITS
    soever
    0.43
     we
    0.27
     they
    0.24
    upon
    0.22
    SOEVER
    0.18
     she
    0.17
    -ever
    0.17
    /how
    0.17
     you
    0.16
    ãĥ¼ãĥ©
    0.16
    Act Density 0.046%

    No Known Activations