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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "well" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oro
    -0.15
    ray
    -0.15
    emi
    -0.14
    ounty
    -0.14
    arna
    -0.14
    arius
    -0.14
     Robertson
    -0.14
    κÎŃ
    -0.14
    gap
    -0.14
    nob
    -0.14
    POSITIVE LOGITS
     underway
    0.23
     intention
    0.22
    ington
    0.21
    INGTON
    0.20
    spring
    0.20
     aware
    0.19
     known
    0.19
    -known
    0.18
    venida
    0.18
     vers
    0.18
    Act Density 0.039%

    No Known Activations