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

    Neuronpedia

    INDEX
    Explanations

    holiday greetings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     philos
    -0.81
     advoc
    -0.76
     princ
    -0.75
     perspect
    -0.75
     pudding
    -0.74
     undermin
    -0.71
     marqu
    -0.71
     commer
    -0.71
     glim
    -0.70
     sensitive
    -0.70
    POSITIVE LOGITS
    9
    1.61
    5
    1.59
    7
    1.59
    6
    1.58
    8
    1.58
    4
    1.49
    3
    1.46
    2
    1.36
    1
    1.30
    98
    1.24
    Act Density 0.052%

    No Known Activations