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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing personal opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases or concepts related to a certain quality or condition, signified by unique character sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.64
     unwelcome
    -0.60
     Skydragon
    -0.54
    é¾
    -0.53
     ATL
    -0.52
    OSP
    -0.52
     Laurent
    -0.51
     Virgin
    -0.50
     SHARES
    -0.50
    CLASSIFIED
    -0.50
    POSITIVE LOGITS
    s
    0.91
    gets
    0.87
    ses
    0.87
    t
    0.85
    hens
    0.85
    ves
    0.83
    d
    0.77
    ti
    0.75
    ve
    0.75
    tic
    0.74
    Act Density 0.247%

    No Known Activations