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

    Neuronpedia

    INDEX
    Explanations

    expressions related to avoidance and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.61
    OrWhiteSpace
    -0.54
     Boas
    -0.53
     Normdatei
    -0.53
    DockStyle
    -0.52
    RenderAtEndOf
    -0.51
    ]--;
    -0.50
    WriteTagHelper
    -0.50
    CPtr
    -0.50
    ︎
    -0.50
    POSITIVE LOGITS
     such
    0.73
     SUCH
    0.69
    such
    0.64
     solches
    0.63
    Such
    0.63
     solche
    0.60
     Such
    0.58
    นั้น
    0.57
    それも
    0.57
     solcher
    0.55
    Act Density 0.264%

    No Known Activations