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

    Neuronpedia

    INDEX
    Explanations

    affirmations and expressions of acceptance or comfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comfortable, okay, acceptable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasForeignKey
    -0.60
     nahilalakip
    -0.54
    utives
    -0.50
    HasBeenSet
    -0.48
     فريبيس
    -0.44
    yych
    -0.44
    lusconi
    -0.44
    奚
    -0.43
    脚注の使い方
    -0.43
    AutoField
    -0.42
    POSITIVE LOGITS
     okay
    1.05
     OK
    1.00
     ok
    0.96
     OKAY
    0.82
    OK
    0.79
     comfortable
    0.78
    okay
    0.78
    Okay
    0.76
     Ok
    0.73
     acceptable
    0.73
    Act Density 0.065%

    No Known Activations