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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activities or information available on the internet

    oai_token-act-pair · gpt-3.5-turbo

    references to content or activities available on the internet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itarian
    -0.72
    actic
    -0.70
    gery
    -0.66
    ppe
    -0.65
    azo
    -0.65
    ogly
    -0.64
    msg
    -0.64
     Scal
    -0.63
    itar
    -0.62
    chest
    -0.62
    POSITIVE LOGITS
    ntil
    0.82
     srfAttach
    0.79
    eatures
    0.76
     Tonight
    0.69
     indoors
    0.68
     cheaply
    0.67
    aturdays
    0.67
    ridges
    0.65
    ô
    0.64
     throughout
    0.63
    Act Density 0.137%

    No Known Activations