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

    Neuronpedia

    INDEX
    Explanations

    instances where something or someone has secured a position or status in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a position or location within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gery
    -0.75
    aeus
    -0.72
    duct
    -0.67
    catch
    -0.67
    use
    -0.66
    selves
    -0.64
    clone
    -0.63
    owner
    -0.62
     neglig
    -0.62
    ully
    -0.62
    POSITIVE LOGITS
     pedest
    0.78
     theaters
    0.75
     prestigious
    0.74
    elight
    0.72
     UNESCO
    0.71
     RTX
    0.68
     civilized
    0.68
     exalted
    0.67
     Nanto
    0.66
     Normandy
    0.66
    Act Density 0.323%

    No Known Activations