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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to emotions and states of being, particularly indicating confusion or inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     most
    -0.60
     deemed
    -0.53
     suggested
    -0.48
     global
    -0.47
    most
    -0.46
     specific
    -0.46
     llama
    -0.45
    نظر
    -0.45
     team
    -0.45
     vse
    -0.44
    POSITIVE LOGITS
    AsUp
    0.96
    OGND
    0.90
     MainAxisSize
    0.89
     Мексичка
    0.88
    MethodManager
    0.88
     defaultstate
    0.88
    AccessorTable
    0.86
    principalColumn
    0.85
    帖最后由
    0.85
    
    0.85
    Act Density 0.155%

    No Known Activations