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

    Neuronpedia

    INDEX
    Explanations

    instances where something is done by someone 'with' a certain characteristic or in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matter
    -0.80
    olt
    -0.79
    TPP
    -0.78
    FFFF
    -0.78
    PIN
    -0.77
    ulf
    -0.74
    ulet
    -0.73
    ItemTracker
    -0.73
    Strange
    -0.73
    NESS
    -0.72
    POSITIVE LOGITS
     plenty
    1.11
     regard
    1.08
     varying
    1.07
     exceptions
    1.04
     apologies
    1.01
     some
    0.99
     occasional
    0.98
     attendant
    0.97
     regards
    0.96
     notable
    0.92
    Act Density 0.116%

    No Known Activations