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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and programming

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns and terms related to children or youth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SIGN
    -0.63
     deleg
    -0.62
     srfAttach
    -0.61
     nond
    -0.61
    ASED
    -0.61
     commons
    -0.60
    MENTS
    -0.58
     compr
    -0.58
     definite
    -0.57
    isSpecialOrderable
    -0.57
    POSITIVE LOGITS
    aurus
    1.57
    mith
    1.57
    kaya
    1.45
    peed
    1.44
    layer
    1.41
    peak
    1.38
    hip
    1.36
    hift
    1.35
    cale
    1.34
    ilver
    1.30
    Act Density 0.215%

    No Known Activations