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

    Neuronpedia

    INDEX
    Explanations

    references to financial transactions or warnings

    oai_token-act-pair · gpt-3.5-turbo

    references to financial concepts such as payday loans and flags for content moderation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imates
    -0.85
    ists
    -0.74
    ophysical
    -0.71
    ysis
    -0.71
     kHz
    -0.68
     Joined
    -0.68
    ophile
    -0.68
     equilibrium
    -0.68
    olver
    -0.67
    ablishment
    -0.66
    POSITIVE LOGITS
     Turing
    0.80
    chall
    0.79
    bor
    0.74
    lit
    0.72
    road
    0.71
    brid
    0.71
    bled
    0.70
    MENTS
    0.70
    ment
    0.69
    nton
    0.69
    Act Density 0.023%

    No Known Activations