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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote combinations or mixtures of elements or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tanooga
    -0.68
    ⓧ
    -0.68
     calendriers
    -0.67
    #+#
    -0.65
     nemico
    -0.63
    skosten
    -0.61
     jouets
    -0.61
    RenderAtEndOf
    -0.59
    toid
    -0.58
     logiciels
    -0.58
    POSITIVE LOGITS
     combining
    0.92
     combines
    0.89
    combination
    0.86
    Combining
    0.86
     combination
    0.85
     Combining
    0.84
     combinations
    0.82
     between
    0.82
     combine
    0.79
     kombin
    0.78
    Act Density 0.352%

    No Known Activations