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

    Neuronpedia

    INDEX
    Explanations

    references to resignations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resignation."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oos
    -0.80
    gran
    -0.69
     Glob
    -0.67
     Huck
    -0.66
    prop
    -0.66
    Cop
    -0.65
    asters
    -0.63
    ohyd
    -0.60
     Starr
    -0.59
     Collider
    -0.57
    POSITIVE LOGITS
     resignation
    1.23
     resign
    0.94
    ptin
    0.92
     srfAttach
    0.91
    isSpecialOrderable
    0.84
    icter
    0.82
     resigned
    0.82
    essment
    0.76
     downfall
    0.74
    terness
    0.74
    Act Density 0.003%

    No Known Activations