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

    Neuronpedia

    INDEX
    Explanations

    phrases related to captions in photos

    oai_token-act-pair · gpt-3.5-turbo

    references to images or visual elements in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aterasu
    -0.77
     incorpor
    -0.61
    anke
    -0.60
     streng
    -0.60
    staking
    -0.60
     staggered
    -0.60
     anchor
    -0.59
     competitiveness
    -0.59
    iqueness
    -0.57
    hement
    -0.57
    POSITIVE LOGITS
     largeDownload
    0.74
    ccording
    0.72
    Copyright
    0.67
    STR
    0.65
    endra
    0.64
    Anonymous
    0.62
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.59
    wise
    0.59
    aban
    0.59
    Compl
    0.58
    Act Density 0.082%

    No Known Activations