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

    Neuronpedia

    INDEX
    Explanations

    themes of trust and reassurance in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ°ãĥ«
    -0.15
    ruh
    -0.14
    reject
    -0.14
    ijd
    -0.14
    atham
    -0.14
     Troy
    -0.14
     Speakers
    -0.14
    unan
    -0.14
    _ascii
    -0.14
     reject
    -0.14
    POSITIVE LOGITS
    clc
    0.17
    ooth
    0.16
     eventually
    0.15
    agedList
    0.14
    ardy
    0.14
    uze
    0.14
     ultimately
    0.14
    éģİ
    0.14
    AdapterFactory
    0.14
    158
    0.13
    Act Density 0.183%

    No Known Activations