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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating similarity or sameness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Royal
    -0.57
     Walkover
    -0.53
     Grand
    -0.53
    Royal
    -0.48
     En
    -0.48
     Frank
    -0.46
    En
    -0.45
     mano
    -0.44
    uage
    -0.44
    marshall
    -0.44
    POSITIVE LOGITS
     étrang
    0.94
     theory
    0.86
    AccessorTable
    0.84
     theories
    0.84
    GOTREF
    0.83
     Theories
    0.81
     THEORY
    0.81
    theory
    0.79
     doubtnut
    0.78
     resourceCulture
    0.78
    Act Density 0.113%

    No Known Activations