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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating settling or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MAC
    -0.75
    Cu
    -0.68
    SPONSORED
    -0.67
     encour
    -0.63
    Champ
    -0.62
    ucha
    -0.61
    Serv
    -0.60
    IBLE
    -0.59
    iew
    -0.59
     portray
    -0.59
    POSITIVE LOGITS
    ntil
    0.87
     fate
    0.69
    iphate
    0.67
     monog
    0.66
     srfAttach
    0.64
     reservation
    0.64
    waters
    0.63
     settling
    0.63
     footing
    0.62
     bets
    0.62
    Act Density 0.132%

    No Known Activations