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

    Neuronpedia

    INDEX
    Explanations

    expressions of willingness to engage or act

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

    willingness to act or commit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.71
    AndEndTag
    -0.65
    tvguidetime
    -0.60
    rrggbb
    -0.60
    DockStyle
    -0.59
    enumi
    -0.58
     Infórmanos
    -0.54
    NameInMap
    -0.54
    abetes
    -0.53
    IsMutable
    -0.53
    POSITIVE LOGITS
     willingness
    1.66
     unwillingness
    1.05
    willing
    0.92
    Willing
    0.91
     Willing
    0.88
     reluctance
    0.87
     eagerness
    0.78
     commitment
    0.72
     readiness
    0.70
     желание
    0.69
    Act Density 0.006%

    No Known Activations