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

    Neuronpedia

    INDEX
    Explanations

    references to deception and betrayal in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .inject
    -0.15
    734
    -0.15
    ighth
    -0.15
    uros
    -0.15
    znik
    -0.14
     KeyValue
    -0.14
     Prev
    -0.13
    llx
    -0.13
     Applies
    -0.13
    umbs
    -0.13
    POSITIVE LOGITS
     lead
    0.32
     lands
    0.32
     leads
    0.31
     cul
    0.29
     landed
    0.27
     led
    0.27
     land
    0.26
    lead
    0.26
     cost
    0.25
     results
    0.25
    Act Density 0.210%

    No Known Activations