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

    Neuronpedia

    INDEX
    Explanations

    actions involving leading or directing others in a physical or metaphorical manner

    oai_token-act-pair · gpt-3.5-turbo

    events related to pursuits or chases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pots
    -0.72
    âĶĢâĶĢâĶĢâĶĢ
    -0.69
    oint
    -0.61
     conditional
    -0.61
    plates
    -0.59
     lett
    -0.59
    rice
    -0.58
    atching
    -0.58
     gif
    -0.57
    cup
    -0.57
    POSITIVE LOGITS
     Steps
    0.88
     journey
    0.86
     toward
    0.84
     footsteps
    0.83
     steps
    0.83
     err
    0.82
     winding
    0.82
     path
    0.82
     journeys
    0.81
     towards
    0.80
    Act Density 0.500%

    No Known Activations