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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a certain type of emphasis or focus, typically highlighting a specific quality or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or a sense of vagueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VEL
    -0.66
    OPE
    -0.66
     Expansion
    -0.64
    VM
    -0.62
     Examination
    -0.61
    ULT
    -0.60
    PT
    -0.59
    Ultra
    -0.58
    idate
    -0.57
    ODE
    -0.57
    POSITIVE LOGITS
    entimes
    0.89
    nered
    0.88
    ling
    0.79
    heartedly
    0.77
    erd
    0.75
    hearted
    0.75
    cast
    0.74
    led
    0.74
    lier
    0.74
    entially
    0.71
    Act Density 0.037%

    No Known Activations