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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions or maneuvers

    oai_token-act-pair · gpt-3.5-turbo

    strategic actions or planning related to competitive scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wordpress
    -0.66
     renamed
    -0.65
    ãĥ¯ãĥ³
    -0.64
    gem
    -0.63
    option
    -0.63
     commissioned
    -0.62
    wrote
    -0.58
     rave
    -0.58
    cia
    -0.58
     refers
    -0.57
    POSITIVE LOGITS
     maximize
    0.88
     undet
    0.84
     avoid
    0.81
     minimize
    0.81
     lest
    0.80
     regain
    0.78
     chances
    0.76
     reap
    0.75
     survive
    0.75
     escape
    0.74
    Act Density 0.474%

    No Known Activations