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

    Neuronpedia

    INDEX
    Explanations

    specific mentions or instances of rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tik
    -0.78
    icer
    -0.75
     Samar
    -0.68
    ogene
    -0.68
    gm
    -0.67
    ishly
    -0.66
    vous
    -0.65
    fitting
    -0.64
    ãĥĨãĤ£
    -0.63
    argo
    -0.63
    POSITIVE LOGITS
     rankings
    1.00
     ranking
    0.91
     Rankings
    0.89
    Rank
    0.81
     contenders
    0.80
     algorithm
    0.78
     Ranking
    0.76
    âĺħâĺħ
    0.73
     contender
    0.71
     algorithms
    0.71
    Act Density 0.040%

    No Known Activations