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

    Neuronpedia

    INDEX
    Explanations

    references to origins or historical beginnings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to origins or foundational aspects of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indemn
    -0.74
    affer
    -0.72
    uron
    -0.68
    isites
    -0.67
    owler
    -0.66
    umbn
    -0.66
    roph
    -0.66
    orneys
    -0.65
    opol
    -0.64
    apter
    -0.64
    POSITIVE LOGITS
     Roots
    0.93
     roots
    0.91
    roots
    0.77
    lore
    0.77
    hips
    0.76
    stones
    0.72
    itious
    0.71
     ingrained
    0.71
    é»Ĵ
    0.69
    waters
    0.68
    Act Density 0.025%

    No Known Activations