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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "close" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with proximity or nearness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vich
    -0.67
    ayers
    -0.65
     manifests
    -0.65
     Anarchy
    -0.64
    osterone
    -0.63
    amins
    -0.61
    ahan
    -0.60
    çķ
    -0.59
    ghazi
    -0.59
    AME
    -0.58
    POSITIVE LOGITS
     close
    3.63
    close
    2.71
     Close
    2.45
    Close
    2.33
     closer
    2.02
     closest
    1.81
     clos
    1.47
     closing
    1.40
     closes
    1.39
     closely
    1.33
    Act Density 0.017%

    No Known Activations