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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the ability or process of learning various skills or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lights
    -0.75
    Choice
    -0.73
    listed
    -0.71
    prem
    -0.68
    closed
    -0.68
    termination
    -0.67
    hur
    -0.65
     Appears
    -0.63
     Gow
    -0.63
     Bolton
    -0.62
    POSITIVE LOGITS
     cope
    1.12
     treat
    1.12
     differentiate
    1.11
     improve
    1.10
     identify
    1.09
     manipulate
    1.09
     behave
    1.09
     make
    1.04
     apply
    1.04
     teach
    1.03
    Act Density 0.087%

    No Known Activations