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

    Neuronpedia

    INDEX
    Explanations

    words related to uniqueness or singularity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "singular."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITNESS
    -0.90
    PLIED
    -0.81
    OTO
    -0.80
    EAR
    -0.74
     Epstein
    -0.74
    ERAL
    -0.73
    ublic
    -0.72
    HOME
    -0.71
    IRED
    -0.69
    UV
    -0.68
    POSITIVE LOGITS
    ities
    1.21
    ity
    1.09
     singular
    0.97
    theless
    0.96
    itarian
    0.88
    itar
    0.88
     jour
    0.86
     ç¥ŀ
    0.83
     identifiers
    0.80
     identifier
    0.80
    Act Density 0.007%

    No Known Activations