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

    Neuronpedia

    INDEX
    Explanations

    terms related to frequency or occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OFDb
    -0.82
    adaptiveStyles
    -0.82
    <unused68>
    -0.81
    <unused41>
    -0.81
    <unused74>
    -0.81
    <unused52>
    -0.81
    <unused79>
    -0.81
    <unused51>
    -0.81
    <unused16>
    -0.81
    <unused42>
    -0.81
    POSITIVE LOGITS
     Sab
    0.40
    .
    0.39
     Last
    0.39
    sg
    0.39
     Additionally
    0.38
     occasional
    0.37
    st
    0.37
     The
    0.37
     occasionally
    0.37
    alt
    0.34
    Act Density 0.291%

    No Known Activations