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

    Neuronpedia

    INDEX
    Explanations

    names or references to political leaders

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms or references to ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.65
     Leilan
    -0.58
    SIGN
    -0.54
     Presidents
    -0.52
    eport
    -0.52
    ilater
    -0.52
    ãĤ¡
    -0.52
     organising
    -0.51
     fuss
    -0.51
    estern
    -0.50
    POSITIVE LOGITS
    ources
    0.95
    omew
    0.83
    lightly
    0.83
    atisf
    0.80
    aying
    0.80
    terday
    0.78
    ourcing
    0.78
    ometime
    0.77
    outhern
    0.77
    ustain
    0.76
    Act Density 0.327%

    No Known Activations