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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to specific topics or subjects of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ops
    -0.16
    Occurrences
    -0.15
    ibel
    -0.15
    uo
    -0.14
    uzzi
    -0.14
    iná
    -0.14
     Kelly
    -0.14
    uÃŃ
    -0.14
    太éĥİ
    -0.13
     Samar
    -0.13
    POSITIVE LOGITS
    fuse
    0.15
     McCart
    0.14
    EA
    0.14
     Jennings
    0.14
    axes
    0.14
    adir
    0.13
    west
    0.13
    fit
    0.13
    inance
    0.13
    istant
    0.13
    Act Density 0.071%

    No Known Activations