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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that indicate relationships or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rete
    -0.15
    237
    -0.15
    anch
    -0.15
    ese
    -0.14
    IRR
    -0.14
    RLF
    -0.14
     Kun
    -0.14
     prive
    -0.14
    272
    -0.14
     Reynolds
    -0.14
    POSITIVE LOGITS
    vasive
    0.19
    dez
    0.17
     ob
    0.17
    habi
    0.16
    itsu
    0.16
    ëł´
    0.16
     invasive
    0.15
     excessive
    0.15
     overposting
    0.15
    iland
    0.15
    Act Density 0.122%

    No Known Activations