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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning a specific acronym (PL) followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group or organization known as the PLO

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansas
    -0.84
    ria
    -0.82
    Downloadha
    -0.81
    real
    -0.78
    lia
    -0.78
    wid
    -0.78
    rians
    -0.74
    hide
    -0.73
    rian
    -0.72
    sem
    -0.72
    POSITIVE LOGITS
    ACE
    0.98
    ATE
    0.95
    OSS
    0.95
    OY
    0.93
    OAD
    0.92
    INK
    0.92
    OGR
    0.91
    AIN
    0.89
    ANC
    0.89
    AST
    0.88
    Act Density 0.007%

    No Known Activations