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

    Neuronpedia

    INDEX
    Explanations

    words related to stopping or pausing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    halting or stopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bisch
    -0.35
     sabido
    -0.34
     exposiciones
    -0.33
     mostrarse
    -0.32
     recovered
    -0.32
     olympique
    -0.32
     añadido
    -0.32
     benefits
    -0.32
    recovered
    -0.31
     orina
    -0.31
    POSITIVE LOGITS
     halted
    1.00
     halt
    0.92
    Halt
    0.83
     halting
    0.82
     stopp
    0.81
     Halt
    0.79
     stop
    0.77
    stop
    0.75
     stoppage
    0.74
     stopped
    0.73
    Act Density 0.034%

    No Known Activations