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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical contact and movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to warmth and comfort in challenging situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Malays
    -0.70
     Revision
    -0.60
     Australians
    -0.60
     Harper
    -0.60
    clinton
    -0.60
     Conservatives
    -0.60
    hillary
    -0.58
     Journalism
    -0.58
    Pakistan
    -0.58
     Clintons
    -0.58
    POSITIVE LOGITS
     unsuspecting
    0.83
     undet
    0.82
    )).
    0.76
     eternity
    0.71
     prest
    0.71
     desired
    0.70
     blinding
    0.69
     predetermined
    0.68
     unprotected
    0.68
     nearby
    0.66
    Act Density 1.584%

    No Known Activations