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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iscons
    -0.71
    othal
    -0.71
    ð
    -0.67
    bies
    -0.66
    udeau
    -0.65
    umbs
    -0.64
     Ends
    -0.64
    rarily
    -0.61
     Ensure
    -0.61
     Colleges
    -0.59
    POSITIVE LOGITS
    nt
    1.07
     aware
    0.95
     hereby
    0.94
     presently
    0.93
     not
    0.89
     unable
    0.89
    omorphic
    0.89
     indeed
    0.88
     currently
    0.88
     NOT
    0.88
    Act Density 0.176%

    No Known Activations