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

    Neuronpedia

    INDEX
    Explanations

    expressions of affirmation or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bcryptjs
    -0.58
    </>
    -0.56
    ⋮
    -0.55
    İstinadlar
    -0.53
     direct
    -0.52
    ⁩
    -0.51
     &___
    -0.49
    一郎
    -0.49
     Direct
    -0.49
    colato
    -0.47
    POSITIVE LOGITS
    Ah
    0.80
     Ah
    0.80
     ok
    0.77
    saurus
    0.74
     OK
    0.70
     ahh
    0.69
    afficheront
    0.69
     ویکی‌پدیای
    0.68
     Alright
    0.67
    Ok
    0.67
    Act Density 0.089%

    No Known Activations