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

    Neuronpedia

    INDEX
    Explanations

    variants or forms of the word "title."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enta
    -0.18
    arpa
    -0.18
    alez
    -0.17
    acias
    -0.17
    iams
    -0.16
     ><?
    -0.16
    ariat
    -0.16
    yonel
    -0.16
     Ding
    -0.15
    egin
    -0.15
    POSITIVE LOGITS
     tit
    0.27
    tit
    0.27
     Tit
    0.23
    Tit
    0.20
    ular
    0.18
    ania
    0.17
     Titans
    0.17
    ograd
    0.16
    anyl
    0.16
    marsh
    0.16
    Act Density 0.011%

    No Known Activations