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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships between actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymas
    -0.81
    ראלי
    -0.80
    ########.
    -0.75
     Sandler
    -0.75
     Esprit
    -0.73
     integration
    -0.72
     estekak
    -0.72
    formin
    -0.70
     Thierry
    -0.69
     integrator
    -0.69
    POSITIVE LOGITS
    companied
    0.96
     accompanied
    0.86
     accompanies
    0.86
    accompanied
    0.80
     précé
    0.80
    companying
    0.80
    CEED
    0.79
     PROCEED
    0.76
     сопрово
    0.74
     acompañado
    0.72
    Act Density 0.204%

    No Known Activations