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

    Neuronpedia

    INDEX
    Explanations

    expressions of ongoing actions and continuations in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.56
    $_['
    -0.50
     lockers
    -0.46
     Grecs
    -0.45
    Sheikh
    -0.45
     éc
    -0.44
     olympiques
    -0.44
     locker
    -0.44
    Locker
    -0.44
    wiſe
    -0.43
    POSITIVE LOGITS
     Continue
    1.09
     Continues
    1.04
     continue
    1.03
    continue
    0.99
     continuing
    0.94
     continues
    0.94
    Continue
    0.94
     continued
    0.93
     continuance
    0.91
     CONTINUE
    0.88
    Act Density 0.098%

    No Known Activations