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

    Neuronpedia

    INDEX
    Explanations

    texts discussing expertise or mastery in various skills

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express knowledge or understanding of actions and skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vertisement
    -0.74
    atform
    -0.74
    bridge
    -0.74
    POST
    -0.68
    enture
    -0.66
     hereafter
    -0.64
    idon
    -0.64
    inth
    -0.63
    swick
    -0.63
    76561
    -0.62
    POSITIVE LOGITS
     lucky
    0.86
     fragile
    0.83
     much
    0.83
     to
    0.82
     important
    0.80
     difficult
    0.80
     messed
    0.79
    itzer
    0.79
     hard
    0.78
     fucked
    0.76
    Act Density 0.051%

    No Known Activations