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

    Neuronpedia

    INDEX
    Explanations

    phrases related to newsletter subscriptions and well-wishes

    oai_token-act-pair · gpt-3.5-turbo

    references to media and communication platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     into
    -0.75
     onto
    -0.72
    into
    -0.71
     Into
    -0.64
     INTO
    -0.63
    utenberg
    -0.63
    onite
    -0.60
    ene
    -0.57
    omo
    -0.55
    ategory
    -0.55
    POSITIVE LOGITS
     Murd
    0.54
     cancelled
    0.52
     Cance
    0.51
    operated
    0.51
     Glad
    0.49
     fired
    0.48
     Dise
    0.48
     McDonnell
    0.48
    Destroy
    0.46
     RELEASE
    0.46
    Act Density 0.926%

    No Known Activations