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

    Neuronpedia

    INDEX
    Explanations

    information about potential transactions or deals between different entities

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or implications regarding potential actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perished
    -0.73
    opath
    -0.71
     complains
    -0.69
     Attacks
    -0.65
     Lies
    -0.64
     wandered
    -0.64
     deserts
    -0.62
     Disease
    -0.62
    opathic
    -0.62
    Error
    -0.61
    POSITIVE LOGITS
     appease
    1.11
     bolster
    1.02
     pave
    0.99
     catapult
    0.90
     alleviate
    0.88
     boost
    0.88
     lure
    0.87
     complicate
    0.86
     allow
    0.86
     propel
    0.86
    Act Density 0.268%

    No Known Activations