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

    Neuronpedia

    INDEX
    Explanations

    words related to elongation or extension

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lengthening or prolonging a concept or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iance
    -0.75
    ELF
    -0.74
    iquette
    -0.73
    ãĥīãĥ©
    -0.69
     Doctrine
    -0.68
    opoulos
    -0.67
    DragonMagazine
    -0.67
    Ops
    -0.66
    olicited
    -0.64
    Availability
    -0.64
    POSITIVE LOGITS
    thens
    1.37
    thening
    1.20
     leng
    1.14
     prolong
    1.06
     shorten
    0.86
     adjourn
    0.86
    umbers
    0.84
    slow
    0.84
    then
    0.81
    umber
    0.80
    Act Density 0.017%

    No Known Activations