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

    Neuronpedia

    INDEX
    Explanations

    fast-paced, action-related terms

    oai_token-act-pair · gpt-3.5-turbo

    descriptors that indicate the characteristics or status of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.91
    chwitz
    -0.85
    redits
    -0.84
    uther
    -0.79
    Specific
    -0.77
    atches
    -0.74
    drug
    -0.71
    stri
    -0.71
    cius
    -0.69
    rows
    -0.69
    POSITIVE LOGITS
     nature
    1.08
     version
    0.91
     saga
    0.84
     portion
    0.82
     duo
    0.77
     moniker
    0.77
     aspect
    0.77
     underside
    0.77
     phenomenon
    0.76
     onslaught
    0.76
    Act Density 0.255%

    No Known Activations