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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to contrasting perspectives or options

    oai_token-act-pair · gpt-3.5-turbo

    phrases contrasting two sides or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.75
    dr
    -0.71
    dra
    -0.70
    sung
    -0.69
    äºĶ
    -0.65
    renches
    -0.65
    nz
    -0.65
    âĸĪâĸĪ
    -0.64
    ral
    -0.64
    vill
    -0.64
    POSITIVE LOGITS
     rejoice
    0.65
     applaud
    0.63
     behalf
    0.61
     Uni
    0.61
     congratulations
    0.60
    icka
    0.57
    aciously
    0.54
     assuming
    0.53
    aminer
    0.53
     reconcil
    0.53
    Act Density 0.074%

    No Known Activations