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

    Neuronpedia

    INDEX
    Explanations

    references to historical political scandals and affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SerializedSize
    -0.39
    chooser
    -0.36
    \{\\
    -0.34
    ifikationer
    -0.33
     Rep
    -0.32
    ModelAdmin
    -0.31
     vermogen
    -0.30
     extra
    -0.30
    )}</
    -0.30
    rouw
    -0.30
    POSITIVE LOGITS
    #+#
    0.71
     <<<<<<<<<<<<<<
    0.67
    verwijspagina
    0.63
    AnchorStyles
    0.62
    MLLoader
    0.60
    Jîn
    0.59
    Needle
    0.59
     candle
    0.59
     Needle
    0.58
     mikrofon
    0.58
    Act Density 1.205%

    No Known Activations