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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data processing and military operations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Forward" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    colo
    -0.99
    mingham
    -0.81
    chens
    -0.79
    azo
    -0.79
    gins
    -0.77
    AIN
    -0.74
    abase
    -0.72
    hett
    -0.72
    aret
    -0.71
    tub
    -0.71
    POSITIVE LOGITS
     thinker
    0.79
     thinkers
    0.74
    wards
    0.73
    Ħ¢
    0.68
     reflection
    0.67
    forward
    0.67
     forwarding
    0.67
    ive
    0.67
     collision
    0.66
    ugal
    0.65
    Act Density 0.025%

    No Known Activations