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

    Neuronpedia

    INDEX
    Explanations

    phrases or contexts involving physical movement over objects or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "over."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.72
    illary
    -0.69
    ãĥ¼ãĥĨ
    -0.68
     understatement
    -0.67
    ORY
    -0.67
    uum
    -0.66
    STAR
    -0.64
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.64
    nesota
    -0.64
    imony
    -0.64
    POSITIVE LOGITS
    hang
    1.18
    loading
    1.05
    drive
    1.02
    tones
    1.01
    lord
    1.00
    rule
    0.96
    hung
    0.87
    clock
    0.85
    comes
    0.82
    bearing
    0.81
    Act Density 0.068%

    No Known Activations