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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating accountability and clarity in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     experiment
    -0.15
     tiế
    -0.14
    ifest
    -0.14
    Counts
    -0.14
    ç»ıçIJĨ
    -0.14
     Arguments
    -0.14
     itself
    -0.13
     destinationViewController
    -0.13
     effort
    -0.12
     improv
    -0.12
    POSITIVE LOGITS
    ůst
    0.19
     Recorded
    0.15
    createForm
    0.15
     recording
    0.15
     fotograf
    0.14
     females
    0.14
     územ
    0.14
     Visual
    0.14
     Zombies
    0.14
     ad
    0.14
    Act Density 0.040%

    No Known Activations