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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust and its importance in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anness
    -0.17
    preter
    -0.16
    zar
    -0.16
    urgy
    -0.16
    esel
    -0.16
    uron
    -0.15
    aad
    -0.15
    _ASSUME
    -0.15
    oproject
    -0.15
    estring
    -0.15
    POSITIVE LOGITS
    worth
    0.20
    /conf
    0.18
     Morrow
    0.18
    ably
    0.16
    able
    0.15
    ucker
    0.15
    worthy
    0.14
    ir
    0.14
     خاطر
    0.14
    full
    0.14
    Act Density 0.041%

    No Known Activations