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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to industrial events or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to events and their related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aspberry
    -0.65
    enos
    -0.62
    angelo
    -0.61
    cook
    -0.60
    olars
    -0.60
    natureconservancy
    -0.59
    cious
    -0.58
    akeru
    -0.56
    eno
    -0.56
    hematic
    -0.55
    POSITIVE LOGITS
     indefinitely
    0.63
     centrif
    0.56
     sidew
    0.54
     Execution
    0.54
     withdrawals
    0.54
     gravity
    0.54
     (âĪĴ
    0.53
     due
    0.52
    Repeat
    0.51
     guiName
    0.51
    Act Density 1.443%

    No Known Activations