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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or action, particularly involving taking off or on something

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and verbs indicating movement or change of state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appa
    -0.75
    ndra
    -0.72
    athy
    -0.68
    ixture
    -0.67
    ili
    -0.65
    IOR
    -0.64
    ells
    -0.64
    orth
    -0.62
    ambo
    -0.61
    eller
    -0.61
    POSITIVE LOGITS
     seriously
    0.83
     lightly
    0.76
    ãĥīãĥ©
    0.73
    */(
    0.73
     Seriously
    0.69
    advant
    0.68
     remed
    0.67
    kef
    0.66
     tumble
    0.64
    æ©
    0.63
    Act Density 0.106%

    No Known Activations