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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the ability or action of doing something

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing potential or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.64
    DERR
    -0.64
     insofar
    -0.62
     Coff
    -0.60
     surn
    -0.60
     Hits
    -0.59
     Wrong
    -0.58
     Seeking
    -0.58
    cens
    -0.58
     Sack
    -0.58
    POSITIVE LOGITS
    't
    1.38
     afford
    1.23
     confidently
    1.10
     safely
    1.09
     easily
    1.05
     concentrate
    1.05
     continue
    0.99
     comfortably
    0.99
     enjoy
    0.95
     proceed
    0.94
    Act Density 0.135%

    No Known Activations