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

    Neuronpedia

    INDEX
    Explanations

    phrases related to knowledge, power, and influence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychological conditions and complex concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izont
    -0.49
     veter
    -0.49
    ificantly
    -0.49
    ensibly
    -0.47
     concess
    -0.43
    itialized
    -0.43
    yss
    -0.43
    oret
    -0.43
     thous
    -0.43
     privately
    -0.42
    POSITIVE LOGITS
    .[
    1.20
    .
    1.16
    *.
    1.05
    .(
    1.01
    +.
    0.99
    .).
    0.97
    .</
    0.97
    .*
    0.96
    ."[
    0.95
    '.
    0.95
    Act Density 1.378%

    No Known Activations