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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce content or signals a new topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Like this:"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uve
    -0.69
     wreck
    -0.58
     offending
    -0.56
     harness
    -0.56
     interpol
    -0.55
    alist
    -0.54
    ment
    -0.53
    mble
    -0.52
    verning
    -0.51
     unloaded
    -0.51
    POSITIVE LOGITS
     Cosponsors
    0.73
     Pocket
    0.62
     {*
    0.62
    pees
    0.61
     Choose
    0.60
     Provided
    0.58
    Click
    0.57
    hover
    0.57
     Click
    0.57
    iPhone
    0.56
    Act Density 0.052%

    No Known Activations