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

    Neuronpedia

    INDEX
    Explanations

    concepts related to direction or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    voir
    -0.15
     váºŃy
    -0.15
    osci
    -0.15
    ErrorHandler
    -0.15
    ëĭ´
    -0.15
    odyn
    -0.15
    ê
    -0.14
    ANTA
    -0.14
    ocha
    -0.14
    ved
    -0.14
    POSITIVE LOGITS
    ality
    0.33
    ally
    0.28
    ivity
    0.21
     toward
    0.20
    eer
    0.19
    als
    0.19
    less
    0.19
    ward
    0.18
    nal
    0.18
     arrows
    0.18
    Act Density 0.037%

    No Known Activations