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

    Neuronpedia

    INDEX
    Explanations

    phrases related to receiving promotional offers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to frequency of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Recomm
    -0.90
    CDC
    -0.80
    ACTED
    -0.78
    åĤ
    -0.74
    kamp
    -0.70
    roots
    -0.70
    atche
    -0.69
    rollers
    -0.69
    lda
    -0.69
    LAN
    -0.69
    POSITIVE LOGITS
     occasional
    1.09
     bouts
    1.08
     glimps
    0.93
    etheless
    0.90
     periodic
    0.88
     commer
    0.84
     rains
    0.84
     occas
    0.84
     exceptions
    0.83
     strugg
    0.82
    Act Density 0.005%

    No Known Activations