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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing opinions or arguments

    oai_token-act-pair · gpt-3.5-turbo

    commas in complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concess
    -0.78
    EngineDebug
    -0.70
    rid
    -0.67
     readings
    -0.67
     output
    -0.64
    Output
    -0.64
     outputs
    -0.63
    reth
    -0.61
     ausp
    -0.60
    eco
    -0.59
    POSITIVE LOGITS
     whom
    1.18
     Jr
    1.15
    who
    1.07
     Sr
    1.04
     who
    1.01
    Jr
    0.98
    whose
    0.94
     whose
    0.91
     aka
    0.84
    doms
    0.78
    Act Density 0.349%

    No Known Activations