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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance, core, or significant aspects of topics being discussed

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the central or foundational components of various subjects or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.75
    ruciating
    -0.70
     RELEASE
    -0.67
    apon
    -0.65
    DERR
    -0.64
    byter
    -0.64
    orneys
    -0.63
    ufact
    -0.63
    intend
    -0.62
    apons
    -0.60
    POSITIVE LOGITS
     thereof
    0.88
    waters
    0.86
    most
    0.85
    strings
    0.76
    verse
    0.74
    mast
    0.72
    gro
    0.71
    Theme
    0.71
     of
    0.71
    plates
    0.69
    Act Density 0.064%

    No Known Activations