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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a susceptibility to negative conditions or outcomes

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

    prone to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.54
    DockStyle
    -0.52
    Handlung
    -0.49
    spoke
    -0.48
     CreateTagHelper
    -0.46
     ICommand
    -0.46
    客様
    -0.45
     Compañ
    -0.44
     obje
    -0.44
    AtPosition
    -0.44
    POSITIVE LOGITS
     prone
    0.88
    prone
    0.63
     predis
    0.54
     propensity
    0.53
     predisposition
    0.45
     cenderung
    0.44
     دچار
    0.44
     tienden
    0.44
     LIABLE
    0.44
     liable
    0.43
    Act Density 0.025%

    No Known Activations