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

    Neuronpedia

    INDEX
    Explanations

    discussions and references about people's experiences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /up
    -0.15
    shore
    -0.15
    มาย
    -0.14
    tro
    -0.14
    æ²¢
    -0.14
    adt
    -0.14
     Olson
    -0.14
    ught
    -0.14
    ahren
    -0.13
    jak
    -0.13
    POSITIVE LOGITS
     away
    0.39
     off
    0.36
     down
    0.35
     out
    0.33
     up
    0.33
     apart
    0.28
     into
    0.25
     back
    0.23
     Away
    0.21
     forth
    0.21
    Act Density 0.470%

    No Known Activations