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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty and variability in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.63
    TabIndex
    -0.55
     PhpStorm
    -0.54
     OnInit
    -0.53
    ArgsConstructor
    -0.52
     partiellement
    -0.50
    DNEY
    -0.50
    sizeCache
    -0.49
    SuspendLayout
    -0.49
     partially
    -0.48
    POSITIVE LOGITS
     comunque
    0.85
     Regardless
    0.82
    Regardless
    0.80
    Whatever
    0.69
     Whatever
    0.68
    hichever
    0.68
     uiteindelijk
    0.64
    etheless
    0.64
    总之
    0.64
     begge
    0.63
    Act Density 0.218%

    No Known Activations