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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrasal verbs indicating movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.71
    úrese
    -0.69
    saraba
    -0.68
     }}"></
    -0.67
    ArgsConstructor
    -0.65
     BorderLayout
    -0.64
    tvguidetime
    -0.60
     Himo
    -0.60
     ProtoMessage
    -0.59
    ).__
    -0.58
    POSITIVE LOGITS
    InjectAttribute
    0.61
     the
    0.57
    chargez
    0.52
    queles
    0.52
     releasing
    0.48
    atiker
    0.48
    的是
    0.48
     klart
    0.47
    надца
    0.47
    Voici
    0.46
    Act Density 0.296%

    No Known Activations