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

    Neuronpedia

    INDEX
    Explanations

    references to "the" as a definite article

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.74
    sekret
    -0.64
    ︎
    -0.55
    orthand
    -0.53
     κάθε
    -0.52
    addComponent
    -0.51
     <<<<<<<<<<<<<<
    -0.51
     Ludlow
    -0.51
     blew
    -0.50
    MathML
    -0.50
    POSITIVE LOGITS
     few
    0.82
    abetes
    0.82
    SOUNDBITE
    0.81
    LookAnd
    0.74
    Few
    0.66
    MLLoader
    0.65
     FEW
    0.65
     Few
    0.64
    few
    0.63
    +#+
    0.63
    Act Density 0.022%

    No Known Activations