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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong positive evaluations or affirmations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resolutions or responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Welsh
    -0.73
     hint
    -0.63
     Icelandic
    -0.63
     Holmes
    -0.62
     hints
    -0.62
     flank
    -0.62
     snippets
    -0.60
     Dynamics
    -0.60
    glers
    -0.59
     Cruiser
    -0.59
    POSITIVE LOGITS
    pec
    1.20
    olver
    1.18
    ourced
    1.15
    igned
    1.11
    umption
    1.09
    olute
    1.07
    olutions
    1.06
    ign
    1.05
    ounding
    1.04
    itance
    1.04
    Act Density 0.012%

    No Known Activations