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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with the word "Anyone."

    oai_token-act-pair · gpt-3.5-turbo

    the word "anyone," indicating discussions about people in general

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.75
    bows
    -0.74
    tnc
    -0.63
     Maze
    -0.61
     Maiden
    -0.61
     puppies
    -0.60
    FU
    -0.60
     Hound
    -0.59
    ocamp
    -0.57
    ulk
    -0.57
    POSITIVE LOGITS
     else
    1.59
    else
    1.25
     Else
    1.16
    Else
    1.15
     who
    1.12
    who
    1.07
     wishing
    0.92
     acquainted
    0.91
     interested
    0.91
    soever
    0.89
    Act Density 0.040%

    No Known Activations