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

    Neuronpedia

    INDEX
    Explanations

    phrases related to keys, both physical and metaphorical

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words that indicate keys or solutions to problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.75
    ibia
    -0.71
    Marie
    -0.70
    abama
    -0.68
    bats
    -0.65
    jad
    -0.64
     Cock
    -0.63
    iless
    -0.62
    aucuses
    -0.62
     Pengu
    -0.62
    POSITIVE LOGITS
     ignition
    0.97
     unlocking
    0.95
     decrypt
    0.84
     bearer
    0.74
    ceptor
    0.74
    orah
    0.74
     pi
    0.73
     transcription
    0.70
     decoding
    0.65
     unlock
    0.65
    Act Density 0.166%

    No Known Activations