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

    Neuronpedia

    INDEX
    Explanations

    examples of facts or statistics

    oai_token-act-pair · gpt-3.5-turbo

    issues related to health, environmental risks, and socio-political conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.50
    osite
    -0.49
    ãĥ´
    -0.45
     pione
    -0.45
     Wem
    -0.45
    ij士
    -0.44
    arling
    -0.44
     Cele
    -0.43
    alez
    -0.43
    ãĤ©
    -0.43
    POSITIVE LOGITS
     whilst
    0.76
     Belfast
    0.73
     despite
    0.68
    .[
    0.68
    .–
    0.67
    .<
    0.66
     while
    0.65
    .#
    0.63
     ©
    0.61
    .—
    0.60
    Act Density 0.971%

    No Known Activations