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

    Neuronpedia

    INDEX
    Explanations

    words that indicate the notion of contribution or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogram
    -0.14
    AtPath
    -0.14
     knack
    -0.14
     underestimate
    -0.14
    opa
    -0.13
    Ïħγ
    -0.13
    ãĥĭãĥ¼
    -0.13
    osemite
    -0.13
     shorthand
    -0.13
    stdafx
    -0.13
    POSITIVE LOGITS
     dimension
    0.27
     another
    0.27
     insult
    0.24
    another
    0.23
     layers
    0.22
    -value
    0.20
     additional
    0.20
     Layers
    0.20
     dimensions
    0.20
     layer
    0.20
    Act Density 0.050%

    No Known Activations