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

    Neuronpedia

    INDEX
    Explanations

    variations of the prefix "mis" indicating incorrectness or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.63
     صوتيه
    -0.54
     Cæsar
    -0.53
    InitVars
    -0.53
    marginHorizontal
    -0.51
    
    -0.51
    età
    -0.51
    ClientSize
    -0.50
    ⓘ
    -0.49
     ferma
    -0.46
    POSITIVE LOGITS
    matched
    0.58
    representation
    0.57
    interpretation
    0.56
    haps
    0.55
    givings
    0.55
    évaluateur
    0.54
    ogyn
    0.53
    fits
    0.53
    firing
    0.53
    fires
    0.53
    Act Density 0.271%

    No Known Activations