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

    Neuronpedia

    INDEX
    Explanations

    prepositions used to introduce a reason or explanation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "For" followed by a number or statement of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ady
    -0.65
     undet
    -0.61
    SPONSORED
    -0.59
     unexplained
    -0.57
     credibility
    -0.57
     alive
    -0.56
     thought
    -0.55
    ogene
    -0.54
    azes
    -0.54
    kered
    -0.54
    POSITIVE LOGITS
     For
    2.68
    For
    1.89
     To
    1.69
     Of
    1.50
     By
    1.46
     With
    1.45
     In
    1.40
     Until
    1.40
     From
    1.40
     Because
    1.39
    Act Density 0.024%

    No Known Activations