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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "talk" at a high activation level

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "talk" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emale
    -0.74
    arte
    -0.68
    boa
    -0.65
    iverpool
    -0.64
    orius
    -0.63
    hews
    -0.62
    uilt
    -0.62
    ritional
    -0.60
    rypt
    -0.60
     [|
    -0.59
    POSITIVE LOGITS
     about
    1.00
    about
    0.83
     aloud
    0.83
     smack
    0.83
     ABOUT
    0.82
     frankly
    0.81
     louder
    0.79
     loudly
    0.78
    ebus
    0.77
    ative
    0.75
    Act Density 0.056%

    No Known Activations