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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and concepts related to instructions, procedures, and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uga
    -0.65
    phia
    -0.61
    arij
    -0.60
    ¿½
    -0.60
    £ı
    -0.60
    agna
    -0.60
    pher
    -0.59
    ģĸ
    -0.59
    pherd
    -0.59
    elvet
    -0.57
    POSITIVE LOGITS
    ickets
    0.66
    itiveness
    0.59
    ById
    0.56
    Cooldown
    0.56
     sqor
    0.55
     Refresh
    0.53
     Craw
    0.52
    Houston
    0.52
     Boulder
    0.50
     Spotify
    0.50
    Act Density 0.972%

    No Known Activations