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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating similarity or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chg
    -0.17
    еÑĢÑĪ
    -0.16
     POSSIBILITY
    -0.15
    ile
    -0.15
    enate
    -0.14
    orrh
    -0.14
    heet
    -0.14
    ilyn
    -0.13
    riculum
    -0.13
    heets
    -0.13
    POSITIVE LOGITS
    -sort
    0.22
    -ÑĤаки
    0.17
     like
    0.16
     semi
    0.16
    thing
    0.15
    /s
    0.15
     sort
    0.15
    ewhat
    0.15
     thing
    0.15
    ANO
    0.15
    Act Density 0.033%

    No Known Activations