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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" and its variations, indicating comparisons or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.63
    StoryboardSegue
    -0.59
    complexContent
    -0.56
    Hozzáférés
    -0.56
    ArrowToggle
    -0.55
    AccessorTable
    -0.54
    jsii
    -0.54
    SequentialGroup
    -0.53
    يكب
    -0.53
    arusian
    -0.53
    POSITIVE LOGITS
    liest
    0.68
    wise
    0.68
    WISE
    0.59
    lier
    0.56
     minded
    0.53
     crazy
    0.52
     unto
    0.51
     clock
    0.49
    wiſe
    0.47
     wise
    0.46
    Act Density 0.113%

    No Known Activations