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

    Neuronpedia

    INDEX
    Explanations

    verbs related to quick or sudden movements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     outgoing
    -0.78
     vows
    -0.64
     miscar
    -0.62
     incoming
    -0.61
    spir
    -0.60
    RF
    -0.60
     phased
    -0.60
    ŃĶ
    -0.60
    £
    -0.58
     behav
    -0.57
    POSITIVE LOGITS
     grips
    0.95
    ggles
    0.95
    pless
    0.93
     capitalize
    0.84
    obin
    0.83
     accommodate
    0.81
    acus
    0.81
     maximize
    0.81
    pload
    0.80
     conserve
    0.80
    Act Density 0.165%

    No Known Activations