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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight absurd or humorous narratives and unconventional scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disegni
    -0.58
     appunto
    -0.56
    ParallelGroup
    -0.55
    Almost
    -0.52
     soldati
    -0.52
     fermée
    -0.52
     becauſe
    -0.51
     samarbeid
    -0.51
     eszköz
    -0.51
     onCancelled
    -0.51
    POSITIVE LOGITS
    rinol
    0.67
     hemor
    0.65
    friger
    0.62
    ∮
    0.61
    twimg
    0.60
    phyla
    0.59
    Thong
    0.59
    orghini
    0.59
     Encyclopedia
    0.58
    ghijklmnop
    0.58
    Act Density 0.515%

    No Known Activations