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

    Neuronpedia

    INDEX
    Explanations

    phrases related to purpose or intention, often involving comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    infinitive phrases involving "to" followed by a verb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crom
    -0.66
    iked
    -0.66
     Halls
    -0.64
     Corpus
    -0.64
     Centauri
    -0.63
     OK
    -0.63
    âĿ
    -0.63
     Gram
    -0.62
     Nile
    -0.61
    istries
    -0.60
    POSITIVE LOGITS
     minimize
    1.00
     imply
    0.97
     recreate
    0.93
     exclude
    0.93
     reassure
    0.91
     deprive
    0.90
     eliminate
    0.90
     remind
    0.89
     preclude
    0.89
     emulate
    0.89
    Act Density 0.043%

    No Known Activations