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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional statements or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hil
    -0.18
     hil
    -0.17
    sert
    -0.15
    ìłĪ
    -0.15
    stakes
    -0.14
    akin
    -0.14
    aken
    -0.14
    achuset
    -0.14
    oupon
    -0.14
    wner
    -0.13
    POSITIVE LOGITS
    gage
    0.18
    anford
    0.16
     Pear
    0.16
    emm
    0.15
    bage
    0.15
     Pearce
    0.14
     currency
    0.14
     Helm
    0.14
    kola
    0.14
    ebo
    0.14
    Act Density 0.003%

    No Known Activations