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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to equivalence and sufficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ĥ
    -0.16
    antu
    -0.15
    onyms
    -0.14
     orth
    -0.13
    umpt
    -0.13
    BackPressed
    -0.13
    ìķĶ
    -0.13
     Checklist
    -0.13
    imedia
    -0.13
     Orth
    -0.12
    POSITIVE LOGITS
     oc
    0.85
    oc
    0.81
    OC
    0.75
     Oc
    0.73
     OC
    0.72
     occ
    0.65
    _oc
    0.63
    .oc
    0.62
     Occ
    0.61
    occ
    0.60
    Act Density 0.181%

    No Known Activations