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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific methods, strategies, or ways of doing things

    oai_token-act-pair · gpt-3.5-turbo

    references to various methods or strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arus
    -0.74
     Wak
    -0.69
    cakes
    -0.68
    cake
    -0.67
    rake
    -0.66
    gin
    -0.66
    pedia
    -0.66
    reported
    -0.66
    ãĥ©ãĥ³
    -0.63
    watching
    -0.62
    POSITIVE LOGITS
     approach
    0.93
     Approach
    0.91
    ahime
    0.84
     toward
    0.77
    lectic
    0.77
    ologies
    0.76
    rait
    0.72
     thereto
    0.72
    oteric
    0.72
    »Ĵ
    0.72
    Act Density 0.022%

    No Known Activations