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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating email subjects or topics of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esternos
    -0.71
    ficult
    -0.70
    ratulations
    -0.66
    pectives
    -0.65
    frastructure
    -0.65
     المعيارى
    -0.65
    Còn
    -0.63
    BibitemShut
    -0.63
    drawal
    -0.63
    EREF
    -0.63
    POSITIVE LOGITS
    Off
    0.56
     Demand
    0.55
    Demand
    0.54
    off
    0.53
    demand
    0.49
     offside
    0.47
     DEMAND
    0.47
     demand
    0.46
    fire
    0.45
     Paused
    0.45
    Act Density 0.099%

    No Known Activations