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

    Neuronpedia

    INDEX
    Explanations

    complex strings of characters at various levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric sequences and upper-case letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itsch
    -0.82
    DonaldTrump
    -0.78
    à©
    -0.72
    taboola
    -0.70
    illary
    -0.70
    âĸ¬
    -0.69
     GOODMAN
    -0.69
    ãĥ¯ãĥ³
    -0.68
    idays
    -0.68
    istries
    -0.67
    POSITIVE LOGITS
    fy
    0.81
    ZX
    0.73
    qq
    0.72
    \">
    0.70
    Bs
    0.68
    XM
    0.67
     Shib
    0.67
    dn
    0.66
    dq
    0.65
     Nab
    0.65
    Act Density 0.074%

    No Known Activations