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

    Neuronpedia

    INDEX
    Explanations

    information related to news events such as incidents and accidents

    oai_token-act-pair · gpt-3.5-turbo

    events involving violence or injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĥĪ
    -0.54
    cedented
    -0.52
    ©¶æ
    -0.52
     SOFTWARE
    -0.49
     LCS
    -0.48
     licens
    -0.48
    eworks
    -0.47
    devices
    -0.47
    DragonMagazine
    -0.47
    ARB
    -0.46
    POSITIVE LOGITS
     consolation
    0.51
     Mim
    0.49
     Omar
    0.49
     drown
    0.48
     slit
    0.47
     afterward
    0.46
     hat
    0.45
    iku
    0.45
     Gael
    0.44
     vomit
    0.44
    Act Density 2.810%

    No Known Activations