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

    Neuronpedia

    INDEX
    Explanations

    phrases related to an individual person taking a particular action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "will" indicating future actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.73
    Lear
    -0.65
    ourke
    -0.64
     misunderstanding
    -0.63
    quickShipAvailable
    -0.63
    reality
    -0.63
    HQ
    -0.60
    Weak
    -0.60
     calcul
    -0.60
     abstraction
    -0.60
    POSITIVE LOGITS
     be
    1.19
     continue
    1.10
     undoubtedly
    1.01
     gladly
    0.97
     doubtless
    0.97
    ows
    0.96
     remain
    0.94
     begin
    0.93
     unveil
    0.93
     join
    0.93
    Act Density 0.200%

    No Known Activations