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

    Neuronpedia

    INDEX
    Explanations

    words related to problems or concerns

    oai_token-act-pair · gpt-3.5-turbo

    references to problems or complications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tsky
    -0.95
    theless
    -0.89
    asts
    -0.85
    emouth
    -0.85
    glas
    -0.83
    urses
    -0.79
    raltar
    -0.75
    cki
    -0.75
    ongyang
    -0.73
    ovy
    -0.73
    POSITIVE LOGITS
     plag
    1.09
     affecting
    0.83
    hooting
    0.82
     tracker
    0.78
    iating
    0.74
     unresolved
    0.74
     arise
    0.73
     relating
    0.72
     stemming
    0.71
     resolved
    0.68
    Act Density 0.041%

    No Known Activations