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

    Neuronpedia

    INDEX
    Explanations

    numerical values and comparisons in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -1.06
    󠁢
    -0.81
     MainAxisSize
    -0.80
     صوتيه
    -0.80
    ={({
    -0.76
     larmes
    -0.75
     leſs
    -0.75
    IsContent
    -0.74
    gradable
    -0.74
    
    -0.74
    POSITIVE LOGITS
     is
    0.56
     will
    0.55
    ScopeManager
    0.55
    enderror
    0.52
    .
    0.51
     to
    0.50
     correctes
    0.49
     was
    0.48
     has
    0.48
    ))
    0.47
    Act Density 0.426%

    No Known Activations