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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential benefits or advantages

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

    "potential to" or similar wording

    np_acts-logits-general · gemini-2.0-flash

    potential and ability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.37
    vielen
    -0.36
     officers
    -0.34
    MCS
    -0.32
    ciuto
    -0.32
     Schließlich
    -0.31
    lichkeiten
    -0.30
     Mehl
    -0.30
     those
    -0.30
     lò
    -0.30
    POSITIVE LOGITS
     ability
    0.63
    ScopeManager
    0.61
     capability
    0.60
     capacity
    0.59
     advantage
    0.58
     tendenza
    0.55
     option
    0.55
    ">//
    0.53
    @[+][
    0.52
     capacité
    0.52
    Act Density 0.182%

    No Known Activations