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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to physical impacts and collisions

    oai_token-act-pair · gpt-3.5-turbo

    actions and events involving movement or changes in state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ican
    -0.69
    ourt
    -0.64
     tackling
    -0.64
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
    appropriate
    -0.61
     playbook
    -0.60
    ourke
    -0.60
     promotion
    -0.59
    fold
    -0.59
    pc
    -0.58
    POSITIVE LOGITS
     beneath
    0.83
     spontaneously
    0.75
    burst
    0.74
     silently
    0.73
     into
    0.73
     slowly
    0.73
     smoothly
    0.73
     underneath
    0.72
     mysteriously
    0.72
     unexpectedly
    0.70
    Act Density 0.271%

    No Known Activations