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

    Neuronpedia

    INDEX
    Explanations

    instances of the preposition "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eigenvectors
    -1.54
     himself
    -1.53
     herself
    -1.50
    ialize
    -1.48
     disability
    -1.44
     prejudice
    -1.42
     itself
    -1.40
    odb
    -1.40
     $(
    -1.39
    ically
    -1.37
    POSITIVE LOGITS
    ®
    1.72
    ¤
    1.56
    than
    1.55
    arma
    1.54
    ¿½
    1.47
    Ļ
    1.47
    etica
    1.47
    ints
    1.45
    aping
    1.45
    clin
    1.39
    Act Density 0.210%

    No Known Activations