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

    Neuronpedia

    INDEX
    Explanations

    specific sequences of letters related to streets or roads

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bou" and related terms, suggesting a focus on topics surrounding banquets or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tiger
    -0.72
    spin
    -0.71
     fixation
    -0.70
     Tigers
    -0.69
     Detected
    -0.68
     Trading
    -0.64
     Slug
    -0.64
    cover
    -0.61
     Breed
    -0.61
     Spy
    -0.61
    POSITIVE LOGITS
    ework
    0.93
    icip
    0.92
    quet
    0.88
    atform
    0.86
    anca
    0.85
    Ĭ
    0.84
    alon
    0.83
    levard
    0.81
    Ĩ
    0.80
    dylib
    0.79
    Act Density 0.017%

    No Known Activations