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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reliance or dependence on particular resources or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terness
    -0.82
    flies
    -0.75
    visor
    -0.74
    Cola
    -0.73
    ONSORED
    -0.73
    zon
    -0.72
    facing
    -0.71
    ahime
    -0.71
    FLAG
    -0.70
    numbered
    -0.70
    POSITIVE LOGITS
     scraps
    0.89
     intuition
    0.84
     brute
    0.83
     imported
    0.83
     intermedi
    0.81
     imports
    0.79
     instinct
    0.79
     unreliable
    0.78
     gimm
    0.77
     donations
    0.76
    Act Density 0.032%

    No Known Activations