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

    Neuronpedia

    INDEX
    Explanations

    phrases identifying characteristics or features of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that state or assert something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itches
    -0.86
    actory
    -0.73
    ffe
    -0.71
    igraph
    -0.67
    ievers
    -0.67
    otte
    -0.67
    commit
    -0.66
    ced
    -0.63
    conn
    -0.63
    iscal
    -0.63
    POSITIVE LOGITS
     admittedly
    1.06
     supposed
    1.03
     meant
    0.99
     basically
    0.97
     essentially
    0.89
     obviously
    0.88
     unlikely
    0.86
     certainly
    0.86
     probably
    0.85
     presumably
    0.85
    Act Density 0.135%

    No Known Activations