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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions and aspects of a process or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.02
    хьтан
    -1.01
     سكانية
    -0.88
    parsedMessage
    -0.84
    StructEnd
    -0.84
    <pad>
    -0.83
    <unused47>
    -0.83
    <unused74>
    -0.83
    <unused41>
    -0.83
    [@BOS@]
    -0.83
    POSITIVE LOGITS
     that
    0.40
     it
    0.35
     certainly
    0.34
     also
    0.33
    1
    0.32
     for
    0.32
     compatible
    0.32
     främ
    0.32
    0
    0.31
    5
    0.31
    Act Density 0.515%

    No Known Activations