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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of content or elements within something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orville
    -0.72
    lüğ
    -0.69
     înainte
    -0.63
     obicei
    -0.60
    lück
    -0.59
     arroz
    -0.59
     @"";
    -0.58
     gluta
    -0.58
    k
    -0.57
    Év
    -0.57
    POSITIVE LOGITS
     Contain
    1.70
     CONTAIN
    1.65
     contains
    1.58
     contain
    1.55
     contained
    1.55
     Contains
    1.54
     enthalten
    1.39
    contain
    1.37
     contient
    1.36
    Contain
    1.34
    Act Density 0.133%

    No Known Activations