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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating vulnerability or susceptibility to various conditions or factors

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

    susceptible to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.51
     päiv
    -0.49
     yrity
    -0.48
    LookAnd
    -0.47
     prière
    -0.47
     vœ
    -0.46
     henkil
    -0.45
    ırl
    -0.44
    Slf
    -0.43
     procès
    -0.43
    POSITIVE LOGITS
     susceptible
    1.82
     susceptibility
    1.69
    ceptibility
    1.44
    ceptible
    1.37
     suscepti
    1.35
     suscep
    1.15
     susceptibles
    1.13
     prone
    0.86
     vulnerable
    0.79
     receptive
    0.75
    Act Density 0.012%

    No Known Activations