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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accompanying elements or additional information

    oai_token-act-pair · gpt-3.5-turbo

    the word "with" used frequently in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orius
    -0.74
    dark
    -0.71
    anos
    -0.67
    -|
    -0.67
    wrong
    -0.66
    iland
    -0.66
    ittal
    -0.65
    itute
    -0.65
     Reincarn
    -0.64
    gging
    -0.63
    POSITIVE LOGITS
     regards
    0.81
    ++++++++
    0.76
     impunity
    0.72
    ++++++++++++++++
    0.72
    è¦ļéĨĴ
    0.71
     fellow
    0.69
    hedral
    0.68
     superst
    0.67
     countless
    0.67
    ãģĤ
    0.67
    Act Density 0.043%

    No Known Activations