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

    Neuronpedia

    INDEX
    Explanations

    phrases related to overcoming obstacles or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating action or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iate
    -0.84
    othe
    -0.80
    ASE
    -0.78
    iest
    -0.76
    Enlarge
    -0.75
    ever
    -0.75
    liest
    -0.71
    ook
    -0.71
    ãĤ½
    -0.71
    yssey
    -0.70
    POSITIVE LOGITS
     sheer
    0.99
     circumstance
    0.97
     virtue
    0.93
    products
    0.93
    laws
    0.90
     hordes
    0.84
     inertia
    0.84
     factors
    0.84
     fear
    0.83
     gunfire
    0.82
    Act Density 0.161%

    No Known Activations