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

    Neuronpedia

    INDEX
    Explanations

    lines of code or technical commands written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    equality and assignment operations in coding or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     braces
    -0.71
    zynski
    -0.70
    ergy
    -0.69
     resume
    -0.63
    eding
    -0.63
     establishment
    -0.63
     breed
    -0.62
    algia
    -0.61
    anni
    -0.60
    wcs
    -0.60
    POSITIVE LOGITS
    ãĥīãĥ©ãĤ´ãĥ³
    1.04
    PsyNetMessage
    0.96
    CVE
    0.92
    76561
    0.88
    saf
    0.85
    ãĥ´ãĤ¡
    0.84
    true
    0.84
    mc
    0.83
    imm
    0.82
    mint
    0.82
    Act Density 0.013%

    No Known Activations