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

    Neuronpedia

    INDEX
    Explanations

    words related to change or instability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FormatException
    -0.16
     îł
    -0.16
    ippo
    -0.15
    BITS
    -0.15
    _vlog
    -0.14
    wort
    -0.14
    edly
    -0.14
    åªĴ
    -0.14
     <*>
    -0.14
    _UNLOCK
    -0.14
    POSITIVE LOGITS
    ing
    0.20
    Ing
    0.19
     ing
    0.18
    419
    0.17
    ÂŃing
    0.17
    èµ·æĿ¥
    0.17
    antes
    0.16
    ying
    0.16
    -ing
    0.16
    742
    0.15
    Act Density 0.163%

    No Known Activations