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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data analysis and discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating oversight or neglect in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usalem
    -0.74
    robe
    -0.63
    oeuv
    -0.62
    esm
    -0.61
    quished
    -0.58
    iphate
    -0.58
    unte
    -0.58
     bombed
    -0.58
     Photograph
    -0.58
    hibited
    -0.57
    POSITIVE LOGITS
     misconceptions
    0.79
     misunderstanding
    0.74
     relates
    0.73
     misunderstand
    0.72
     explan
    0.70
     causation
    0.69
     misconception
    0.68
     methodological
    0.68
     assumptions
    0.67
     nutshell
    0.67
    Act Density 1.001%

    No Known Activations