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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating belief or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.53
    bibitem
    -0.52
    Refer
    -0.52
     moro
    -0.51
     certiorari
    -0.51
    Mord
    -0.51
    期刊论文
    -0.51
    TagMode
    -0.50
    stdc
    -0.50
     Jot
    -0.50
    POSITIVE LOGITS
     وأن
    0.73
     that
    0.65
    unknownFields
    0.60
    χο
    0.58
     évent
    0.58
    ActivityCompat
    0.56
     THAT
    0.56
     ModelExpression
    0.55
     Vikipedi
    0.54
     there
    0.54
    Act Density 0.267%

    No Known Activations