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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vido
    -0.17
    ettes
    -0.15
    enz
    -0.15
    aunch
    -0.15
     brick
    -0.14
     ourselves
    -0.14
     Fair
    -0.14
    GIT
    -0.14
     tinder
    -0.14
     unders
    -0.14
    POSITIVE LOGITS
    idon
    0.18
    ÑģÑĤа
    0.16
    oup
    0.15
    .sul
    0.15
    WithEmail
    0.14
    Derived
    0.14
    ovÃŃ
    0.14
    ¦Ĥ
    0.14
    骨
    0.14
    ycastle
    0.13
    Act Density 0.011%

    No Known Activations