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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aren
    -0.18
     referenced
    -0.18
     transitioning
    -0.17
     prioritize
    -0.17
     weren
    -0.17
     priorit
    -0.16
     confrontation
    -0.16
     mainstream
    -0.15
     relocated
    -0.15
     showcase
    -0.15
    POSITIVE LOGITS
     afterwards
    0.23
     clave
    0.20
     afterward
    0.19
     essay
    0.19
     dur
    0.19
     desired
    0.19
     beh
    0.19
     esteemed
    0.19
     contr
    0.19
     fanc
    0.18
    Act Density 0.259%

    No Known Activations