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

    Neuronpedia

    INDEX
    Explanations

    words related to a sense of inability, vulnerability, or powerlessness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to feelings of helplessness or powerlessness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issue
    -0.85
    anners
    -0.80
    andals
    -0.75
    pheus
    -0.71
    ATT
    -0.71
    aternity
    -0.71
    akes
    -0.70
    occ
    -0.70
    ickr
    -0.70
    paying
    -0.70
    POSITIVE LOGITS
     helpless
    1.32
    ness
    0.99
    nesses
    0.96
    NESS
    0.95
     powerless
    0.88
    ingly
    0.82
     pige
    0.81
    pless
    0.81
     redes
    0.79
     strugg
    0.79
    Act Density 0.012%

    No Known Activations