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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by the preposition 'to'

    oai_token-act-pair · gpt-3.5-turbo

    infinitive verbs and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Concern
    -0.77
    plates
    -0.76
    quartered
    -0.76
    grounds
    -0.76
     Actions
    -0.76
    mails
    -0.75
     Directions
    -0.75
    listed
    -0.74
     Respons
    -0.74
     Integrity
    -0.74
    POSITIVE LOGITS
     achieve
    1.07
     accomplish
    1.05
     solve
    1.03
     evade
    1.02
     make
    1.02
     create
    1.02
     get
    1.02
     overcome
    1.01
     convince
    1.01
     raise
    1.01
    Act Density 0.078%

    No Known Activations