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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific situation or the state of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of negation and their associated implications in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortment
    -0.70
    ancies
    -0.64
     occupancy
    -0.63
     wheelchair
    -0.59
    ricted
    -0.58
    apons
    -0.57
     likeness
    -0.56
    ilings
    -0.56
     utilization
    -0.56
    okingly
    -0.55
    POSITIVE LOGITS
    _.
    0.96
    .
    0.96
    \.
    0.91
     anyway
    0.91
    .</
    0.90
    .#
    0.90
    .*
    0.86
     :-)
    0.82
     anymore
    0.82
    .<
    0.82
    Act Density 0.636%

    No Known Activations