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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the presence of the word "with" followed closely by other significant words or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ogóle
    -0.61
     refirió
    -0.56
     kenapa
    -0.56
    tų
    -0.55
    UnknownFieldSet
    -0.55
     verbatim
    -0.54
    parsedMessage
    -0.54
     magát
    -0.54
    omiast
    -0.54
     mesmas
    -0.53
    POSITIVE LOGITS
     With
    0.86
    With
    0.81
    有了
    0.77
    ostante
    0.70
     knowing
    0.67
    enumeration
    0.63
    Με
    0.63
     ligiloj
    0.62
     Having
    0.61
     hindsight
    0.61
    Act Density 0.065%

    No Known Activations