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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes within a specific context

    oai_token-act-pair · gpt-3.5-turbo

    parenthetical statements and sections related to game titles and their corresponding votes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rain
    -0.60
     Sven
    -0.58
     Aly
    -0.58
     Wash
    -0.57
     Judd
    -0.57
     Wem
    -0.55
     Fancy
    -0.54
     Cascade
    -0.54
     Canary
    -0.53
     Roose
    -0.53
    POSITIVE LOGITS
    ¶æ
    0.75
    âĶĢâĶĢâĶĢâĶĢ
    0.75
    ĥ
    0.69
    Ħ¢
    0.65
    gyn
    0.64
    «ĺ
    0.64
    nil
    0.62
    naire
    0.62
     differential
    0.61
    fman
    0.60
    Act Density 0.321%

    No Known Activations