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

    Neuronpedia

    INDEX
    Explanations

    words related to strength or power

    oai_token-act-pair · gpt-3.5-turbo

    references to strength and effectiveness, particularly in relation to substances or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.95
    fty
    -0.76
     Commissioners
    -0.71
    Ń·
    -0.68
    VEL
    -0.68
    BOOK
    -0.67
     Sett
    -0.67
     Million
    -0.67
     Murd
    -0.65
     Suc
    -0.65
    POSITIVE LOGITS
    iating
    1.37
    iated
    1.33
    iation
    1.28
    iates
    1.12
    iator
    1.10
    iate
    1.06
    iations
    0.97
    ency
    0.93
    encies
    0.91
    ior
    0.88
    Act Density 0.018%

    No Known Activations