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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigations or attempts to solve a problem

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with efforts or actions related to inquiry and investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sac
    -0.66
    croft
    -0.63
     preceding
    -0.61
    cia
    -0.61
    @@@@
    -0.59
    ritical
    -0.59
    tis
    -0.59
     Kinnikuman
    -0.58
    ijk
    -0.57
    eq
    -0.57
    POSITIVE LOGITS
    IUM
    0.71
     renovations
    0.68
     renov
    0.68
    ansen
    0.67
     ducks
    0.64
    ADRA
    0.63
    STD
    0.62
    GGGGGGGG
    0.59
     furiously
    0.59
     cautiously
    0.59
    Act Density 0.278%

    No Known Activations