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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "finish" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oria
    -0.15
    age
    -0.15
    atte
    -0.14
    SI
    -0.14
    tak
    -0.14
    inda
    -0.13
    itness
    -0.13
    onte
    -0.13
    sdale
    -0.13
    /from
    -0.13
    POSITIVE LOGITS
     touches
    0.23
     off
    0.22
    er
    0.21
    egan
    0.20
    eren
    0.19
    /start
    0.18
    -off
    0.18
    erd
    0.18
    ings
    0.17
     TOUCH
    0.17
    Act Density 0.029%

    No Known Activations