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

    Neuronpedia

    INDEX
    Explanations

    verbs related to beginning and starting

    oai_token-act-pair · gpt-3.5-turbo

    elements related to social activities and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢİ
    -0.59
     theirs
    -0.52
     hers
    -0.51
    .).
    -0.51
     .)
    -0.50
    .}
    -0.50
     Dane
    -0.49
     pic
    -0.49
    .),
    -0.49
    .)
    -0.49
    POSITIVE LOGITS
    ngth
    0.69
    gradation
    0.59
    querade
    0.57
    ĻĤ
    0.57
    è¦ļéĨĴ
    0.55
    itialized
    0.55
     guiName
    0.54
    emort
    0.54
    arate
    0.53
    olation
    0.51
    Act Density 1.236%

    No Known Activations