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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "catch" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashed
    -0.19
    hei
    -0.17
    udu
    -0.15
    idon
    -0.15
    deaux
    -0.14
    алом
    -0.14
    med
    -0.14
     rol
    -0.14
    Ń
    -0.14
    ove
    -0.14
    POSITIVE LOGITS
     catching
    0.29
     catch
    0.28
     Catch
    0.28
     caught
    0.27
    Catch
    0.27
    catch
    0.26
    phrase
    0.26
     catches
    0.26
    caught
    0.24
     glimpse
    0.23
    Act Density 0.025%

    No Known Activations