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

    Neuronpedia

    INDEX
    Explanations

    words related to stability and being well-supported

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stability and vulnerability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oys
    -0.85
    hem
    -0.77
    asms
    -0.74
    Hyper
    -0.71
    GBT
    -0.69
    76561
    -0.67
    icon
    -0.66
    asia
    -0.65
    actus
    -0.65
    anooga
    -0.62
    POSITIVE LOGITS
     footing
    1.44
    SourceFile
    0.85
     defe
    0.78
     arrang
    0.77
     grounding
    0.76
     ingred
    0.75
    enance
    0.72
     teasp
    0.70
    puter
    0.70
    DragonMagazine
    0.70
    Act Density 0.009%

    No Known Activations