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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being obligated or restricted in some way

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to obligations or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MAT
    -0.75
    OTOS
    -0.74
    roma
    -0.72
     Trees
    -0.71
    Es
    -0.65
    ciation
    -0.65
    ETHOD
    -0.65
    apa
    -0.64
    PE
    -0.64
    issance
    -0.64
    POSITIVE LOGITS
     bound
    1.31
    bound
    1.02
    binding
    0.89
    sym
    0.80
    gling
    0.77
     lapt
    0.76
    unin
    0.76
     scrut
    0.75
    loads
    0.74
    fold
    0.72
    Act Density 0.007%

    No Known Activations