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

    Neuronpedia

    INDEX
    Explanations

    words related to identification and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦÏģι
    -0.15
     stockholm
    -0.15
    stripe
    -0.14
    ittel
    -0.14
    CRET
    -0.13
    ackbar
    -0.13
    edis
    -0.13
     or
    -0.13
    elian
    -0.13
    arhus
    -0.13
    POSITIVE LOGITS
     soar
    0.23
     climb
    0.22
     ascend
    0.20
     dive
    0.19
     plunge
    0.19
     leap
    0.16
     jump
    0.16
     Builder
    0.16
     ascent
    0.16
     ساز
    0.15
    Act Density 0.027%

    No Known Activations