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

    Neuronpedia

    INDEX
    Explanations

    unexpected or unusual events

    oai_token-act-pair · gpt-3.5-turbo

    unexpected or remarkable events and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verning
    -0.69
     certific
    -0.69
    addy
    -0.64
    versely
    -0.64
     dominant
    -0.64
    osponsors
    -0.63
     tense
    -0.63
     GOODMAN
    -0.63
     stern
    -0.62
    earchers
    -0.61
    POSITIVE LOGITS
     imaginable
    0.72
    ulence
    0.71
     conco
    0.68
     awaits
    0.68
    manship
    0.64
    fell
    0.64
     involving
    0.64
     considering
    0.63
     indeed
    0.63
     stunts
    0.62
    Act Density 0.472%

    No Known Activations