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

    Neuronpedia

    INDEX
    Explanations

    phrases related to high-activity or updates happening at regular intervals

    oai_token-act-pair · gpt-3.5-turbo

    instances of automatic page refreshes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hire
    -0.68
     guarded
    -0.68
    alties
    -0.63
    enture
    -0.61
     clash
    -0.61
    yna
    -0.60
    gan
    -0.60
    elight
    -0.59
    oted
    -0.59
    gement
    -0.59
    POSITIVE LOGITS
     Mechdragon
    0.96
    ubi
    0.79
    dra
    0.70
    asks
    0.69
    UB
    0.69
    md
    0.67
    ãĤ©
    0.66
    psons
    0.65
     Masquerade
    0.65
    omsky
    0.65
    Act Density 0.000%

    No Known Activations