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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating separation or isolation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating separation or isolation from a larger group or system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivot
    -0.74
     enthusi
    -0.74
    Corn
    -0.70
    CVE
    -0.70
     proble
    -0.67
     inhibitor
    -0.67
    KC
    -0.65
    seek
    -0.63
    raq
    -0.63
     toget
    -0.63
    POSITIVE LOGITS
     afar
    0.94
     whence
    0.82
     thence
    0.72
     others
    0.68
     Ble
    0.63
     herd
    0.61
     Ones
    0.60
     what
    0.59
    ainers
    0.59
     reality
    0.58
    Act Density 0.075%

    No Known Activations