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

    Neuronpedia

    INDEX
    Explanations

    phrases related to doors, hinges, and physical actions involving force

    oai_token-act-pair · gpt-3.5-turbo

    words related to inanimate objects and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyah
    -0.74
     Destruction
    -0.70
    ctic
    -0.69
     Tillerson
    -0.66
     Slaughter
    -0.65
    ãĥ¼ãĥ³
    -0.65
    GO
    -0.65
    ãģª
    -0.64
    gur
    -0.64
    ques
    -0.63
    POSITIVE LOGITS
    rings
    0.90
    bats
    0.89
    ratulations
    0.87
    tone
    0.86
    lash
    0.82
    redients
    0.82
    ocry
    0.79
    irection
    0.79
    elist
    0.79
    hots
    0.72
    Act Density 0.014%

    No Known Activations