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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing explanations or additional information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "is" indicating ongoing states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itches
    -0.73
    actory
    -0.68
    umbs
    -0.66
    ievers
    -0.64
    lex
    -0.63
    conn
    -0.63
    icts
    -0.62
    oice
    -0.61
    otte
    -0.60
    icators
    -0.60
    POSITIVE LOGITS
     admittedly
    0.98
     supposed
    0.98
     meant
    0.95
     basically
    0.93
     presumably
    0.87
     essentially
    0.87
     unlikely
    0.87
     comprised
    0.86
     currently
    0.86
     probably
    0.86
    Act Density 0.130%

    No Known Activations