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

    Neuronpedia

    INDEX
    Explanations

    references to searching or seeking in a context of various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a search for something or a desire to identify specific items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nown
    -0.74
    anas
    -0.69
    claimed
    -0.68
    stem
    -0.67
    rament
    -0.63
    cert
    -0.62
    wealth
    -0.62
    Downloadha
    -0.61
     Kills
    -0.60
    death
    -0.60
    POSITIVE LOGITS
     suspic
    0.78
    ahead
    0.74
    ared
    0.72
    emouth
    0.71
    ative
    0.70
    ãĤ¶
    0.69
     ahead
    0.69
     headlights
    0.69
     horizont
    0.66
    irection
    0.66
    Act Density 0.023%

    No Known Activations