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

    Neuronpedia

    INDEX
    Explanations

    terms related to research and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tape
    -0.17
    tas
    -0.17
    procs
    -0.17
    ën
    -0.16
    iser
    -0.16
    ÏĢο
    -0.15
    voy
    -0.15
    specs
    -0.15
    tos
    -0.14
    нав
    -0.14
    POSITIVE LOGITS
    tright
    0.24
    ched
    0.24
    ches
    0.23
    ching
    0.22
    Ñģ
    0.21
    thood
    0.20
    thouse
    0.18
    ces
    0.18
    ÈĽ
    0.18
    cher
    0.18
    Act Density 0.022%

    No Known Activations