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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the composition or makeup of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that consist of repetitive structures or compositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.82
     pestic
    -0.70
     undermin
    -0.69
     confir
    -0.69
     ingred
    -0.68
    visor
    -0.68
    soType
    -0.68
    ilings
    -0.67
     showc
    -0.67
    itability
    -0.66
    POSITIVE LOGITS
    course
    0.81
     sorts
    0.74
     course
    0.72
    umbn
    0.67
    ventory
    0.65
    quished
    0.64
     Eucl
    0.63
    :-
    0.63
    pty
    0.62
    RIC
    0.61
    Act Density 0.087%

    No Known Activations