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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to formal communications, particularly emails and releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     idols
    -0.74
    rogens
    -0.71
     fruits
    -0.68
    otin
    -0.65
     devs
    -0.63
     Clintons
    -0.63
    avorite
    -0.62
     corpses
    -0.61
     brunt
    -0.61
     brakes
    -0.61
    POSITIVE LOGITS
    statement
    0.87
     behalf
    0.80
     statement
    0.79
    vich
    0.74
    Statement
    0.74
    pared
    0.72
    ixties
    0.71
    iu
    0.70
    yssey
    0.68
    translation
    0.68
    Act Density 0.133%

    No Known Activations