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

    Neuronpedia

    INDEX
    Explanations

    phrases that express new approaches or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DS
    -0.08
    ceed
    -0.08
    ستÙħ
    -0.07
    antar
    -0.07
    maal
    -0.07
    ÑĪев
    -0.07
    rello
    -0.07
    igua
    -0.07
    esa
    -0.07
    mal
    -0.07
    POSITIVE LOGITS
     incl
    0.06
    flux
    0.06
    wis
    0.06
    illery
    0.06
     Mi
    0.05
     McInt
    0.05
    184
    0.05
    enha
    0.05
    jam
    0.05
    fully
    0.05
    Act Density 0.014%

    No Known Activations