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

    Neuronpedia

    INDEX
    Explanations

    recurring themes or structures within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.71
    bewerken
    -0.71
     fhew
    -0.68
     Riproduzione
    -0.65
    
    -0.64
    ſelf
    -0.63
    [++
    -0.62
     quoique
    -0.62
    resave
    -0.61
     صوتيه
    -0.60
    POSITIVE LOGITS
     SwiftUI
    0.62
    threw
    0.61
    verläs
    0.60
     div
    0.58
     anders
    0.58
     java
    0.57
     محفوظة
    0.57
    Judges
    0.56
    "]/
    0.52
     ря
    0.52
    Act Density 0.165%

    No Known Activations