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

    Neuronpedia

    INDEX
    Explanations

    expressions of faith and confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdx
    -0.66
     onStop
    -0.58
    xe
    -0.58
    HORE
    -0.57
    pted
    -0.57
    uccio
    -0.56
     xe
    -0.56
    atura
    -0.55
    éviter
    -0.55
    scriptcase
    -0.55
    POSITIVE LOGITS
     trusting
    1.21
     trust
    1.20
     faith
    1.11
     vertrouwen
    1.07
     confidence
    1.06
    Trust
    1.06
     fiducia
    1.05
    trust
    1.02
     trusts
    1.02
     confiance
    1.01
    Act Density 0.174%

    No Known Activations