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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating social or interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regards
    -0.17
     hindsight
    -0.16
    context
    -0.15
    okrat
    -0.15
    ync
    -0.15
    ular
    -0.15
    uka
    -0.15
     Lights
    -0.14
    olate
    -0.14
    abo
    -0.14
    POSITIVE LOGITS
     consequence
    0.21
     behalf
    0.19
     token
    0.17
    iqu
    0.16
     essentials
    0.15
     default
    0.15
     season
    0.14
     embryo
    0.14
     Outline
    0.14
    IMPLEMENT
    0.14
    Act Density 0.265%

    No Known Activations