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

    Neuronpedia

    INDEX
    Explanations

    words that signify relationships and connections between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eks
    -0.16
    ovah
    -0.15
    Æ°ng
    -0.15
    uckle
    -0.15
     Vulner
    -0.15
    yo
    -0.14
     fre
    -0.14
    yon
    -0.14
    tern
    -0.14
    uce
    -0.14
    POSITIVE LOGITS
    553
    0.15
    isme
    0.15
    'gc
    0.15
    orama
    0.15
    emen
    0.15
    533
    0.14
     Burton
    0.14
    баÑĩ
    0.14
    eman
    0.14
    olith
    0.14
    Act Density 0.010%

    No Known Activations