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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to causation and impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.60
    arakhand
    -0.49
     MonoBehaviour
    -0.49
     ddelweddau
    -0.47
    󠁮
    -0.44
     zimní
    -0.43
    Reds
    -0.42
    fetchone
    -0.42
    SBATCH
    -0.42
     présidenti
    -0.42
    POSITIVE LOGITS
     influenced
    0.59
     caused
    0.58
     by
    0.58
     Caused
    0.57
    DECREF
    0.55
    caused
    0.54
     Powered
    0.53
     powered
    0.52
     aided
    0.51
     sponsored
    0.50
    Act Density 0.784%

    No Known Activations