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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating degrees or levels of expertise or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡t
    -0.18
    ngine
    -0.17
    inan
    -0.16
    /her
    -0.15
    ancellable
    -0.15
     lẽ
    -0.15
    oved
    -0.14
    bservable
    -0.14
     sidewalks
    -0.14
    éal
    -0.14
    POSITIVE LOGITS
    UCH
    0.16
    ech
    0.15
    hari
    0.14
    649
    0.14
    apter
    0.14
    uchi
    0.13
     gd
    0.13
     global
    0.13
     Yi
    0.13
    ouch
    0.13
    Act Density 0.012%

    No Known Activations