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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "contain" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orville
    -0.74
    k
    -0.63
     років
    -0.62
     DPP
    -0.62
     înainte
    -0.60
    lüğ
    -0.60
     arroz
    -0.59
     @"";
    -0.59
    bigskip
    -0.58
    lück
    -0.58
    POSITIVE LOGITS
     CONTAIN
    1.61
     Contain
    1.60
     contains
    1.49
     Contains
    1.46
     contain
    1.44
     contained
    1.40
     Containing
    1.32
     enthalten
    1.31
     Containment
    1.31
    contains
    1.28
    Act Density 0.119%

    No Known Activations