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

    Neuronpedia

    INDEX
    Explanations

    numbers and trigger words related to competitive activities or events

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their related context in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.95
     Hyder
    -0.81
    ãĥ´ãĤ¡
    -0.76
    hern
    -0.75
    çIJ
    -0.73
     Parables
    -0.72
    olitan
    -0.72
     mund
    -0.71
    Els
    -0.71
    sever
    -0.71
    POSITIVE LOGITS
     kill
    1.12
     bake
    1.07
     call
    1.05
     shoot
    1.04
     burn
    1.04
     catch
    1.04
     sell
    1.03
     vote
    1.03
     throw
    1.03
     ride
    1.03
    Act Density 0.269%

    No Known Activations