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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate a state or action

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" and its variations, indicating descriptions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chel
    -0.68
     tips
    -0.67
     Jess
    -0.67
     superst
    -0.63
     Rings
    -0.62
     Trace
    -0.61
    ruciating
    -0.61
     catches
    -0.60
     Kro
    -0.60
     Thousand
    -0.60
    POSITIVE LOGITS
    n
    1.08
    prov
    0.94
    gins
    0.90
    selves
    0.89
    self
    0.89
    usterity
    0.87
    bsite
    0.86
    spect
    0.85
    put
    0.84
    present
    0.82
    Act Density 0.087%

    No Known Activations