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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate existence, state, or occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.69
     يتيمه
    -0.55
     giusta
    -0.55
     giusti
    -0.54
    wrong
    -0.53
    ⓘ
    -0.53
    EndInit
    -0.50
    expandindo
    -0.50
     Ignoring
    -0.49
    right
    -0.49
    POSITIVE LOGITS
     characterized
    1.06
     composed
    1.06
     based
    1.03
     designed
    0.97
     characterised
    0.96
     comprised
    0.96
     divided
    0.93
     accompanied
    0.87
     located
    0.87
     aimed
    0.84
    Act Density 0.987%

    No Known Activations