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

    Neuronpedia

    INDEX
    Explanations

    words related to collecting or gathering data

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forth
    -0.70
    generic
    -0.68
    shr
    -0.68
    lane
    -0.67
    wrap
    -0.65
    brace
    -0.65
    core
    -0.63
    sac
    -0.63
    minent
    -0.62
    con
    -0.62
    POSITIVE LOGITS
     signatures
    0.85
    enance
    0.84
     DATA
    0.81
    STON
    0.74
    ennial
    0.72
    oton
    0.71
     microphones
    0.69
    ãĥķãĤ¡
    0.69
    itatively
    0.69
     collected
    0.69
    Act Density 0.028%

    No Known Activations