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

    Neuronpedia

    INDEX
    Explanations

    calls to action or imperatives related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    imperative verbs related to suggestions or actions that should be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELD
    -0.71
    listed
    -0.67
     Levant
    -0.65
     Slug
    -0.64
    Required
    -0.63
    DERR
    -0.63
     costing
    -0.62
     Born
    -0.60
    æµ
    -0.60
     CV
    -0.59
    POSITIVE LOGITS
     ourselves
    1.14
     celebrate
    1.06
     presume
    1.02
     collectively
    0.99
     conclude
    0.98
     rejoice
    0.98
     discuss
    0.97
     strive
    0.97
     revisit
    0.96
     speculate
    0.94
    Act Density 0.224%

    No Known Activations