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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diverting attention or blame from a particular subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to removing or alleviating burdens or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.71
    eds
    -0.67
    zl
    -0.66
    NEWS
    -0.65
     Cosponsors
    -0.65
    iasm
    -0.63
    zzo
    -0.63
    archives
    -0.63
    interstitial
    -0.63
    ANS
    -0.63
    POSITIVE LOGITS
     Hernandez
    0.66
     inhib
    0.65
     Brett
    0.65
     dam
    0.63
     peril
    0.63
     Rouhani
    0.63
    hern
    0.61
     fragmented
    0.60
     tighter
    0.60
     hers
    0.59
    Act Density 0.241%

    No Known Activations