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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe the characteristics of a thing or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.99
    MessageOf
    -0.73
    <?
    -0.55
    +:+
    -0.51
    <!--
    -0.50
    InjectMocks
    -0.50
     ratify
    -0.49
    ⓧ
    -0.49
    ANDUM
    -0.49
     invokingState
    -0.48
    POSITIVE LOGITS
     bandung
    1.12
     jawa
    1.03
     jaya
    1.01
     Minang
    0.97
     Banjar
    0.97
     maneu
    0.90
     Karang
    0.90
     cartier
    0.89
     Jambi
    0.88
     🤣🤣
    0.85
    Act Density 0.172%

    No Known Activations