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

    Neuronpedia

    INDEX
    Explanations

    words related to dictionaries and their components in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.79
     ſta
    -0.77
    Personendaten
    -0.75
     ſte
    -0.72
     raiſ
    -0.69
    DebuggerNonUser
    -0.68
     tranſ
    -0.67
     pleaſure
    -0.67
    enumii
    -0.66
    ArgsConstructor
    -0.66
    POSITIVE LOGITS
    向
    0.50
    ！
    0.49
    ？
    0.49
    和
    0.48
    （
    0.47
    通
    0.47
    ；
    0.45
    ——
    0.45
    人
    0.45
    古
    0.44
    Act Density 0.161%

    No Known Activations