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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attaching or connecting objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to attaching or connecting items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.70
     Brill
    -0.67
    vo
    -0.67
    izz
    -0.66
     chaotic
    -0.65
    Recipe
    -0.64
    stakes
    -0.64
     ongoing
    -0.63
     Alleg
    -0.63
     Disorder
    -0.63
    POSITIVE LOGITS
     attach
    3.63
     attaches
    2.82
     attaching
    2.15
    attach
    1.85
    Attach
    1.73
     detach
    1.65
     attached
    1.42
     assign
    1.19
     bind
    1.03
     assemble
    0.96
    Act Density 0.025%

    No Known Activations