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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" and variations of its usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.57
    AutoScale
    -0.52
    地图
    -0.51
    线程
    -0.51
    stuffs
    -0.50
    地铁
    -0.49
    线性
    -0.47
    美国
    -0.47
    quele
    -0.47
    那
    -0.47
    POSITIVE LOGITS
     accordance
    1.03
     terms
    0.93
     spite
    0.91
     relation
    0.86
     regards
    0.84
     conjunction
    0.84
     addition
    0.81
     lieu
    0.76
     vitro
    0.69
     regard
    0.68
    Act Density 1.145%

    No Known Activations