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

    Neuronpedia

    INDEX
    Explanations

    terms related to skills or abilities

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romeda
    -0.81
     Pall
    -0.67
     Reloaded
    -0.66
    clipse
    -0.62
     arbitrary
    -0.61
     Wilhelm
    -0.60
     Mald
    -0.58
    pse
    -0.58
    arna
    -0.57
    gran
    -0.57
    POSITIVE LOGITS
     skills
    0.98
    anooga
    0.98
     training
    0.90
    cape
    0.86
     proficiency
    0.86
    poke
    0.86
    linger
    0.85
    learn
    0.82
    mith
    0.82
     chops
    0.81
    Act Density 0.014%

    No Known Activations