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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating confirmation or validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.57
     jullie
    -0.52
    RectangleBorder
    -0.50
    ORPG
    -0.50
    bcryptjs
    -0.48
     menemp
    -0.47
    oredCriteria
    -0.47
    期刊论文
    -0.47
     pylori
    -0.46
    antMatchers
    -0.46
    POSITIVE LOGITS
     confirmation
    1.06
    Confirmation
    0.94
     confirm
    0.91
     confirmed
    0.91
     confirmations
    0.90
    confirmation
    0.89
     Confirmation
    0.89
     confir
    0.85
     Confirm
    0.84
     confirms
    0.82
    Act Density 0.183%

    No Known Activations