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

    Neuronpedia

    INDEX
    Explanations

    mentions of instruction manuals or guides

    oai_token-act-pair · gpt-3.5-turbo

    references to "manuals" or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymes
    -0.80
    nces
    -0.77
    ãĤ¤ãĥĪ
    -0.75
    ween
    -0.71
    addons
    -0.69
    encers
    -0.69
    èª
    -0.69
    orkshire
    -0.68
    adding
    -0.67
    mary
    -0.67
    POSITIVE LOGITS
     dexterity
    1.00
     typew
    0.93
     manual
    0.88
     transmission
    0.87
     exha
    0.85
    urally
    0.78
     override
    0.75
     induction
    0.74
     destro
    0.74
    ©¶æ
    0.72
    Act Density 0.007%

    No Known Activations