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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating a high degree of quality or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aveug
    -0.70
    danno
    -0.64
    toarele
    -0.62
    Gön
    -0.62
    といけない
    -0.59
     écrivain
    -0.58
     épu
    -0.58
     effray
    -0.58
     scrittore
    -0.58
     écri
    -0.57
    POSITIVE LOGITS
    SourceChecksum
    0.74
     nakalista
    0.70
     estimés
    0.65
    angliski
    0.63
    #+#
    0.58
     &___
    0.57
     Highly
    0.56
    RTHOOK
    0.55
     mergeFrom
    0.54
    ungkinan
    0.54
    Act Density 0.148%

    No Known Activations