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

    Neuronpedia

    INDEX
    Explanations

    adjectives followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    past and present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.79
    glers
    -0.71
     congr
    -0.71
    osate
    -0.68
    Congratulations
    -0.67
    inav
    -0.67
     Brist
    -0.62
     Proceed
    -0.62
    ortmund
    -0.60
     Gw
    -0.60
    POSITIVE LOGITS
     certainly
    0.93
     definitely
    0.91
    nt
    0.87
     not
    0.87
     also
    0.86
     nonetheless
    0.81
     downright
    0.79
     NOT
    0.77
     hardly
    0.77
     plagued
    0.74
    Act Density 0.519%

    No Known Activations