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

    Neuronpedia

    INDEX
    Explanations

    references to software releases and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jie
    -0.15
    osti
    -0.15
    arf
    -0.14
    loff
    -0.14
    大åħ¨
    -0.14
    रण
    -0.13
    ndef
    -0.13
     anth
    -0.13
    yleft
    -0.13
    è¾ij
    -0.13
    POSITIVE LOGITS
     beta
    0.43
     Beta
    0.39
    beta
    0.36
     preview
    0.35
    Beta
    0.35
     alpha
    0.34
    -beta
    0.31
    -preview
    0.30
    preview
    0.29
     prere
    0.29
    Act Density 0.091%

    No Known Activations