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

    Neuronpedia

    INDEX
    Explanations

    terms related to faults and blame in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ьаж
    -0.53
    Butterfly
    -0.51
     confinement
    -0.50
     butterfly
    -0.50
     tunnel
    -0.50
    RenderAtEndOf
    -0.49
    thasone
    -0.49
    Tunnel
    -0.49
    WithIdentifier
    -0.48
     Tunnel
    -0.47
    POSITIVE LOGITS
     fault
    0.82
    fault
    0.73
     Fault
    0.73
     jam
    0.72
     blame
    0.68
     jams
    0.66
     Blame
    0.63
    blame
    0.61
     Jam
    0.59
    Fault
    0.59
    Act Density 0.064%

    No Known Activations