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

    Neuronpedia

    INDEX
    Explanations

    compliments or positive remarks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enjoyment or positive feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otomy
    -0.76
    aults
    -0.75
    ouston
    -0.75
    ossession
    -0.74
    moil
    -0.72
    istence
    -0.71
    odan
    -0.69
    otom
    -0.68
     contingency
    -0.67
    incial
    -0.67
    POSITIVE LOGITS
     congr
    1.10
     Especially
    0.89
    Reviewer
    0.85
    Awesome
    0.83
     thank
    0.81
     congratulations
    0.79
     Beautiful
    0.78
     huh
    0.77
    especially
    0.76
     albeit
    0.76
    Act Density 0.494%

    No Known Activations