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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to being new or a beginner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    љи
    -0.52
    thog
    -0.51
    halve
    -0.50
    धान
    -0.49
     waarom
    -0.47
    labelledby
    -0.47
    urably
    -0.46
    respectively
    -0.46
     mít
    -0.45
    arsch
    -0.45
    POSITIVE LOGITS
     newcomer
    1.03
     newcomers
    1.00
     novice
    0.89
     beginner
    0.89
    NewLabel
    0.88
     newbie
    0.87
     newbies
    0.86
    دانشنامهٔ
    0.82
     Newly
    0.82
     rookies
    0.81
    Act Density 0.170%

    No Known Activations