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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and the word "good"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hadiran
    -0.89
     caucus
    -0.88
     myſelf
    -0.88
    osoba
    -0.85
     hornblende
    -0.85
     Caucus
    -0.83
     springfox
    -0.82
     Divina
    -0.82
     Milán
    -0.81
     Heuer
    -0.81
    POSITIVE LOGITS
     good
    1.75
    good
    1.70
     Good
    1.70
     GOOD
    1.67
    Good
    1.63
    GOOD
    1.62
     Goodwin
    1.22
     Goodman
    1.22
     buena
    1.02
    goods
    1.00
    Act Density 0.070%

    No Known Activations