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

    Neuronpedia

    INDEX
    Explanations

    variations of options and choices presented in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eus
    -0.17
    olla
    -0.16
    ablo
    -0.15
    Äįet
    -0.14
    ckill
    -0.14
    otec
    -0.14
    -urlencoded
    -0.14
    éĨ´
    -0.14
    _Desc
    -0.14
    egg
    -0.14
    POSITIVE LOGITS
    акон
    0.17
    ucks
    0.15
     lif
    0.14
     Sunshine
    0.14
    ifice
    0.14
    .Hidden
    0.13
    appy
    0.13
    depending
    0.13
    based
    0.13
     Taken
    0.13
    Act Density 0.089%

    No Known Activations