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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the initiation or progression of actions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     continue
    -0.22
    continue
    -0.21
     continued
    -0.20
     continuing
    -0.20
     continuation
    -0.18
     continues
    -0.18
     continu
    -0.17
    continued
    -0.17
    	continue
    -0.17
     continuar
    -0.17
    POSITIVE LOGITS
    ying
    0.18
     поба
    0.17
     NOTICE
    0.17
     notice
    0.17
    Feel
    0.16
    TLS
    0.15
     taper
    0.15
    lesh
    0.15
     noticing
    0.15
     noticed
    0.15
    Act Density 0.058%

    No Known Activations