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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that include functions or definitions related to states or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intptr
    -0.59
     theme
    -0.54
     surges
    -0.53
     arrows
    -0.52
     Jej
    -0.52
     GIO
    -0.51
     Giro
    -0.51
     arrow
    -0.51
     TOK
    -0.50
     ASR
    -0.50
    POSITIVE LOGITS
    DIPSETTING
    0.77
    tså
    0.74
     cioè
    0.73
    awaiter
    0.72
    mergeFrom
    0.68
    IVEREF
    0.67
    moveToFirst
    0.67
     ovvero
    0.66
    parsedMessage
    0.66
     indipendente
    0.64
    Act Density 0.325%

    No Known Activations