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

    Neuronpedia

    INDEX
    Explanations

    URLs in text

    oai_token-act-pair · gpt-3.5-turbo

    URLs, particularly those starting with "https"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utility
    -0.74
     utilities
    -0.69
     coales
    -0.68
    NetMessage
    -0.64
     trainer
    -0.64
    ricular
    -0.64
     surn
    -0.64
     trainers
    -0.62
     retained
    -0.61
    atorium
    -0.60
    POSITIVE LOGITS
    ://
    1.25
    ONSORED
    0.84
    vernight
    0.81
    :/
    0.80
    ihad
    0.76
    ember
    0.72
    ðŁĺ
    0.71
    twitter
    0.71
    Ô
    0.71
    legraph
    0.70
    Act Density 0.029%

    No Known Activations