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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to preconditions or preliminary contexts in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endregion
    -0.49
    Personensuche
    -0.44
    ictwa
    -0.42
     Signalez
    -0.41
    AddTagHelper
    -0.40
    🟤
    -0.40
    irtschaft
    -0.40
    DataURL
    -0.39
    +:+
    -0.37
    Solución
    -0.36
    POSITIVE LOGITS
     pre
    1.09
     Pre
    0.96
    Pre
    0.92
    pre
    0.81
     pré
    0.77
     PRE
    0.76
    PRE
    0.61
    预
    0.60
     Preg
    0.58
     preexisting
    0.55
    Act Density 0.122%

    No Known Activations