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

    Neuronpedia

    INDEX
    Explanations

    references to community engagement and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rit
    -0.17
    .sent
    -0.15
    iro
    -0.15
    lder
    -0.15
    olet
    -0.15
    blink
    -0.14
    arna
    -0.14
    jal
    -0.14
    ritz
    -0.14
     taking
    -0.14
    POSITIVE LOGITS
    ToFront
    0.27
     forth
    0.25
     alive
    0.20
     into
    0.19
    bring
    0.19
    Bring
    0.19
    bear
    0.18
    Into
    0.18
     together
    0.17
     closer
    0.17
    Act Density 0.102%

    No Known Activations