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

    Neuronpedia

    INDEX
    Explanations

    negations and logical conditions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     etc
    -0.61
     CGFloat
    -0.59
     ‘
    -0.54
     ​​
    -0.53
    Nuorodos
    -0.52
     The
    -0.51
     True
    -0.51
    </h2>
    -0.49
     These
    -0.49
     '';
    -0.49
    POSITIVE LOGITS
    Hozzáférés
    0.83
    ((
    0.80
    protoimpl
    0.79
    enumi
    0.77
    tagHelperRunner
    0.76
     ſche
    0.73
     málaga
    0.70
    (((
    0.69
     niedersachsen
    0.68
     ſtate
    0.68
    Act Density 0.101%

    No Known Activations