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

    Neuronpedia

    INDEX
    Explanations

    words related to agreement or addition

    oai_token-act-pair · gpt-3.5-turbo

    the word "too."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.69
    inarily
    -0.68
    seless
    -0.63
    enance
    -0.59
    icipated
    -0.59
    inated
    -0.58
    hyde
    -0.57
     Hammond
    -0.56
    inators
    -0.55
    eer
    -0.55
    POSITIVE LOGITS
    oths
    0.75
    ħĭ
    0.69
    leep
    0.66
    ould
    0.65
    ISTORY
    0.64
    akening
    0.63
     tempting
    0.63
     guiActiveUn
    0.62
    othe
    0.61
    --------------------------------
    0.61
    Act Density 0.035%

    No Known Activations