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

    Neuronpedia

    INDEX
    Explanations

    conditional and negation phrases in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -1.04
     ་་
    -0.95
     AssemblyCompany
    -0.93
     الرياضيه
    -0.92
     ―――――
    -0.92
    Xna
    -0.91
     $_"
    -0.91
    AsUp
    -0.90
    Демографія
    -0.89
     Theſe
    -0.88
    POSITIVE LOGITS
     ob
    0.59
     h
    0.57
     in
    0.55
     i
    0.54
     
    0.52
     at
    0.52
    ,
    0.48
     (
    0.47
    .
    0.46
     u
    0.45
    Act Density 0.977%

    No Known Activations