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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating action or activity

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "taking" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geon
    -0.76
    vae
    -0.74
    idel
    -0.67
    DN
    -0.67
    ibus
    -0.66
    ledged
    -0.65
    anguages
    -0.65
    ulates
    -0.63
    igrated
    -0.63
    ulate
    -0.63
    POSITIVE LOGITS
     taking
    2.93
    taking
    2.29
     Taking
    1.91
    Taking
    1.81
     seizing
    1.66
     giving
    1.49
     picking
    1.48
     bringing
    1.48
     stealing
    1.48
     capturing
    1.47
    Act Density 0.028%

    No Known Activations