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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate hands-on or practical experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lef
    -0.15
     Mate
    -0.14
    odore
    -0.14
    -hearted
    -0.14
    loyd
    -0.14
    nt
    -0.14
    æį·
    -0.14
    -song
    -0.13
     Ones
    -0.13
     Jennings
    -0.13
    POSITIVE LOGITS
    /down
    0.21
     approach
    0.21
    /on
    0.20
    edly
    0.20
    ery
    0.19
    /off
    0.18
    urance
    0.18
     Approach
    0.17
    /full
    0.17
    appro
    0.17
    Act Density 0.198%

    No Known Activations