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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions involving loss or destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >",
    -0.81
    AnimationsModule
    -0.79
    ⓧ
    -0.77
     kasarigan
    -0.76
    findpost
    -0.71
     חיצוניים
    -0.71
     '\\;'
    -0.67
    ]){
    -0.66
    "]);
    -0.66
     linkovi
    -0.66
    POSITIVE LOGITS
    BufferException
    0.56
    ruptcy
    0.53
     AssemblyCompany
    0.49
     by
    0.49
     a
    0.47
    acks
    0.47
     vì
    0.46
    griffe
    0.46
     לצ
    0.45
    unci
    0.45
    Act Density 0.428%

    No Known Activations