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

    Neuronpedia

    INDEX
    Explanations

    words related to string instruments and tension

    oai_token-act-pair · gpt-3.5-turbo

    words related to being strong or strength

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĺ
    -0.67
     Morrow
    -0.63
     CODE
    -0.63
    phasis
    -0.62
     Guarant
    -0.60
    externalActionCode
    -0.59
    phant
    -0.58
    ño
    -0.58
     Correction
    -0.58
    cloth
    -0.57
    POSITIVE LOGITS
    lasses
    1.12
    emouth
    0.73
    ĭ
    0.73
    ulative
    0.72
    userc
    0.70
    eness
    0.69
    unal
    0.69
    nir
    0.68
    ging
    0.67
    entious
    0.66
    Act Density 0.007%

    No Known Activations