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

    Neuronpedia

    INDEX
    Explanations

    words related to potential struggles or challenges

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to risk and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.59
     Jury
    -0.57
     Coffin
    -0.53
    osphere
    -0.51
    riot
    -0.51
    uran
    -0.50
    robe
    -0.50
    rome
    -0.49
     subsistence
    -0.49
     Exile
    -0.49
    POSITIVE LOGITS
    fully
    0.82
    lessly
    0.79
     wise
    0.79
    bably
    0.71
    imately
    0.66
    ually
    0.65
    ally
    0.63
     crept
    0.63
    wise
    0.63
     flowed
    0.61
    Act Density 0.601%

    No Known Activations