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

    Neuronpedia

    INDEX
    Explanations

    language related to discussing and reporting various kinds of information or activities

    oai_token-act-pair · gpt-3.5-turbo

    significant terms and phrases related to evidence and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anyways
    -0.63
    +.
    -0.63
     respectively
    -0.58
     themselves
    -0.55
     anyway
    -0.54
     scen
    -0.52
     shenan
    -0.52
    FTWARE
    -0.51
    itton
    -0.50
    ullivan
    -0.48
    POSITIVE LOGITS
     is
    1.32
     represents
    1.31
     refers
    1.30
     has
    1.28
     belongs
    1.28
     denotes
    1.27
     reflects
    1.27
     comprises
    1.27
     consists
    1.25
     constitutes
    1.25
    Act Density 0.566%

    No Known Activations