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

    Neuronpedia

    INDEX
    Explanations

    names of specific entities or brands

    oai_token-act-pair · gpt-3.5-turbo

    references to systems, structures, or methodologies within various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.70
    ALSE
    -0.67
    teness
    -0.64
    ardon
    -0.64
    blank
    -0.64
     YES
    -0.63
    requisite
    -0.63
    =~
    -0.63
     curiosity
    -0.59
     caveat
    -0.59
    POSITIVE LOGITS
     fared
    1.40
     interacts
    1.24
     reacted
    1.16
     handled
    1.11
     interacted
    1.09
     handles
    1.08
     cope
    1.07
     relate
    1.06
     stacks
    1.05
     compares
    1.05
    Act Density 0.239%

    No Known Activations