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

    Neuronpedia

    INDEX
    Explanations

    keywords related to advancement or progress

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Forward" or its variants in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    colo
    -0.88
    chens
    -0.77
    gins
    -0.77
    azo
    -0.76
    hod
    -0.74
    lez
    -0.71
    mingham
    -0.70
    redit
    -0.69
    AIN
    -0.69
    ENE
    -0.66
    POSITIVE LOGITS
     thinker
    0.72
    wards
    0.72
    forward
    0.69
    Ħ¢
    0.69
    ward
    0.69
     characterization
    0.68
    Iterator
    0.67
     thinkers
    0.66
     reflection
    0.64
     forwarding
    0.64
    Act Density 0.021%

    No Known Activations