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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that modify or describe various subjects in detail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Technique
    -0.73
    Unknown
    -0.70
     Tiny
    -0.70
    Offline
    -0.69
    Ult
    -0.69
    Widget
    -0.68
    USS
    -0.68
     guiName
    -0.68
    Wik
    -0.67
    ©¶æ¥µ
    -0.67
    POSITIVE LOGITS
     ray
    0.75
    -
    0.74
     affairs
    0.72
     care
    0.70
     offending
    0.69
    âĢij
    0.69
     fide
    0.64
     law
    0.64
    âĢIJ
    0.64
     justice
    0.64
    Act Density 0.331%

    No Known Activations