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

    Neuronpedia

    INDEX
    Explanations

    phrases related to seizing things

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seized" or its variations related to taking possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grad
    -0.78
    Distance
    -0.77
     Xavier
    -0.71
    Opt
    -0.69
     Optional
    -0.64
    rees
    -0.62
    linear
    -0.61
    Poly
    -0.61
    inity
    -0.61
     UV
    -0.61
    POSITIVE LOGITS
     seized
    3.59
     seize
    2.58
     seizing
    2.46
     confiscated
    2.32
     seizure
    1.96
     seizures
    1.66
     raided
    1.65
     confisc
    1.50
     snatched
    1.49
     recovered
    1.35
    Act Density 0.026%

    No Known Activations