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

    Neuronpedia

    INDEX
    Explanations

    words related to reloading or preparing for action

    oai_token-act-pair · gpt-3.5-turbo

    references to game mechanics or attributes related to loading and reloading in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shatter
    -0.76
     Constantin
    -0.75
    Constructed
    -0.74
     Vit
    -0.72
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
     Chandra
    -0.67
    ENC
    -0.64
     Gael
    -0.64
    IDENT
    -0.63
    FORE
    -0.63
    POSITIVE LOGITS
    oad
    1.40
    erness
    1.03
    loads
    0.95
    dress
    0.93
    sworth
    0.89
    ragon
    0.88
    emouth
    0.85
    ients
    0.83
    ysis
    0.83
    load
    0.81
    Act Density 0.009%

    No Known Activations