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

    Neuronpedia

    INDEX
    Explanations

    symbols or special characters used in text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ãķ
    -0.18
    irmware
    -0.18
    alez
    -0.16
    erset
    -0.15
     Merrill
    -0.14
     Neu
    -0.14
     Technique
    -0.14
    onium
    -0.14
     COMMON
    -0.14
    omination
    -0.14
    POSITIVE LOGITS
    |}↵
    0.19
    inz
    0.18
     contador
    0.18
     jel
    0.17
     societal
    0.16
     motif
    0.15
     Layout
    0.15
     mechanically
    0.15
     surgeries
    0.15
     testimonials
    0.15
    Act Density 0.007%

    No Known Activations