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

    Neuronpedia

    INDEX
    Explanations

    the repetition of the word "over" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.80
    DoubleQuotes
    -0.61
    clable
    -0.60
    corbic
    -0.57
     sonata
    -0.57
     spiegel
    -0.57
     cân
    -0.56
    ForResult
    -0.56
     Extras
    -0.55
    طني
    -0.55
    POSITIVE LOGITS
     over
    1.74
     över
    0.92
    raszam
    0.84
     peste
    0.77
     über
    0.76
     across
    0.72
     върху
    0.67
     sobre
    0.66
     under
    0.66
     about
    0.63
    Act Density 0.129%

    No Known Activations