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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical restraint or control

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms associated with holding or maintaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocaly
    -0.68
    obo
    -0.64
    Downloadha
    -0.63
    orescent
    -0.63
    acha
    -0.62
    ļéĨĴ
    -0.62
    xxxxxxxx
    -0.62
    xon
    -0.62
     starve
    -0.62
     extortion
    -0.61
    POSITIVE LOGITS
    hold
    1.51
    ings
    1.08
    held
    1.04
    erness
    1.01
    scl
    0.99
    sworth
    0.97
    holding
    0.94
    s
    0.92
    ers
    0.90
    sburg
    0.89
    Act Density 0.020%

    No Known Activations