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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thon
    -0.18
    ún
    -0.15
    ukan
    -0.14
    illes
    -0.13
    wap
    -0.13
    _failure
    -0.13
    注æĦı
    -0.13
     fucking
    -0.13
    æk
    -0.13
    пеÑĢ
    -0.13
    POSITIVE LOGITS
    .Solid
    0.14
     Rica
    0.14
    :
    0.14
    iffies
    0.14
    ricks
    0.14
    uh
    0.13
    èĻŁ
    0.13
    éry
    0.13
    613
    0.13
    erm
    0.13
    Act Density 0.108%

    No Known Activations