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

    Neuronpedia

    INDEX
    Explanations

    phrases related to anticipation and future events

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "forward"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uff
    -0.64
    chens
    -0.62
    tein
    -0.62
    oda
    -0.62
    ripp
    -0.61
    redit
    -0.60
     DAM
    -0.60
    rolley
    -0.59
    ById
    -0.59
    AIN
    -0.59
    POSITIVE LOGITS
    forward
    1.08
     forward
    1.00
    olicy
    0.92
    Forward
    0.87
     forwards
    0.87
    wards
    0.86
     Forward
    0.84
     forwarding
    0.81
    shore
    0.76
    comings
    0.74
    Act Density 0.018%

    No Known Activations