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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the process or journey of progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    le
    -0.17
    roz
    -0.17
    ro
    -0.15
    ONUS
    -0.15
    ui
    -0.14
    Ïĥμο
    -0.14
    lood
    -0.14
    attern
    -0.14
    isy
    -0.14
    933
    -0.14
    POSITIVE LOGITS
     coast
    0.23
     beginning
    0.20
     conception
    0.20
     pillar
    0.20
    soup
    0.20
    elles
    0.19
    idea
    0.19
     soup
    0.18
    mers
    0.18
    generation
    0.18
    Act Density 0.084%

    No Known Activations