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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "some"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "some."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enance
    -0.81
    gon
    -0.71
    meet
    -0.69
    SPONSORED
    -0.67
    ruption
    -0.66
    sburgh
    -0.66
     borne
    -0.65
    raid
    -0.64
    ettes
    -0.64
    agents
    -0.63
    POSITIVE LOGITS
    place
    1.03
    ones
    0.98
    how
    0.94
    body
    0.87
     semblance
    0.84
     degree
    0.77
     consolation
    0.76
     unspecified
    0.75
     extent
    0.71
     obscure
    0.70
    Act Density 0.115%

    No Known Activations