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

    Neuronpedia

    INDEX
    Explanations

    statements that express disbelief or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONTAL
    -0.14
    igin
    -0.14
    .hm
    -0.14
    ov
    -0.14
     æ¾
    -0.14
    ÑĤен
    -0.13
    Ïĩή
    -0.13
    TypeInfo
    -0.13
    iness
    -0.13
     latter
    -0.13
    POSITIVE LOGITS
    resco
    0.17
    ystack
    0.16
    itore
    0.15
    umbn
    0.15
    andest
    0.14
    complexContent
    0.14
    arih
    0.14
    rong
    0.14
    thalm
    0.14
    ordova
    0.13
    Act Density 0.607%

    No Known Activations