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

    Neuronpedia

    INDEX
    Explanations

    possessive forms of "is" indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     penetr
    -0.17
    oldur
    -0.16
    acionales
    -0.15
    ildo
    -0.14
    uhe
    -0.14
    νο
    -0.14
    unner
    -0.14
    Pressed
    -0.14
    esture
    -0.13
    contri
    -0.13
    POSITIVE LOGITS
     been
    0.49
     become
    0.40
     come
    0.38
     gotten
    0.37
    been
    0.37
     done
    0.34
     Been
    0.33
     had
    0.32
     BEEN
    0.32
     taken
    0.32
    Act Density 0.078%

    No Known Activations