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

    Neuronpedia

    INDEX
    Explanations

    words related to significant impacts or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itta
    -0.18
    531
    -0.16
    532
    -0.16
    atalog
    -0.15
    altar
    -0.15
    igne
    -0.15
    Comple
    -0.15
    753
    -0.14
    hammer
    -0.14
     Augusta
    -0.14
    POSITIVE LOGITS
    ListItemIcon
    0.15
     stiff
    0.14
     competitive
    0.14
    NEXT
    0.14
    象
    0.14
    ubern
    0.14
     fork
    0.14
    ELLOW
    0.13
    uez
    0.13
    oplay
    0.13
    Act Density 0.004%

    No Known Activations