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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or progression

    oai_token-act-pair · gpt-3.5-turbo

    words related to movement and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.74
    oret
    -0.69
    cffff
    -0.66
    ateurs
    -0.65
    owment
    -0.65
    ancies
    -0.65
     Plain
    -0.64
    nown
    -0.62
    acular
    -0.61
    xual
    -0.61
    POSITIVE LOGITS
    step
    0.98
     pedal
    0.97
     slide
    0.83
     onward
    0.82
     heel
    0.81
    forward
    0.80
     forward
    0.78
    pull
    0.76
     downwards
    0.76
    Charge
    0.75
    Act Density 0.392%

    No Known Activations