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

    Neuronpedia

    INDEX
    Explanations

    combinations of numbers indicating specific shapes or formations

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical measures or performance metrics in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verified
    -0.70
    latest
    -0.68
    pleasant
    -0.66
    risk
    -0.66
    vier
    -0.65
    valid
    -0.64
    educ
    -0.64
    atre
    -0.63
    assy
    -0.63
    cart
    -0.63
    POSITIVE LOGITS
     formation
    0.83
     centr
    0.74
     wings
    0.72
     overtime
    0.71
    llor
    0.68
     combo
    0.65
     wing
    0.64
     Ply
    0.63
     combination
    0.62
     combinations
    0.61
    Act Density 0.052%

    No Known Activations