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

    Neuronpedia

    INDEX
    Explanations

    phrases related to allowing or permitting actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preceded
    -0.66
    peak
    -0.65
    :{
    -0.64
    den
    -0.62
    rose
    -0.62
    abel
    -0.61
    rand
    -0.60
    ....
    -0.59
    illon
    -0.59
     insofar
    -0.59
    POSITIVE LOGITS
     entire
    1.14
     slightest
    1.05
     same
    1.04
     latter
    1.03
     strongest
    1.00
     largest
    0.99
     remainder
    0.97
     smallest
    0.94
     widest
    0.94
     whole
    0.94
    Act Density 0.320%

    No Known Activations