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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing feelings or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dom
    -0.71
    ograp
    -0.68
    VG
    -0.67
    Cor
    -0.66
    Cow
    -0.65
    Comb
    -0.65
    ivas
    -0.64
    ograph
    -0.64
    eneg
    -0.64
    Sac
    -0.63
    POSITIVE LOGITS
    etheless
    0.74
     refuel
    0.66
     hurry
    0.66
     liking
    0.62
     rebirth
    0.62
     alternatively
    0.61
     reborn
    0.61
     doub
    0.60
     grunt
    0.60
     reversible
    0.60
    Act Density 1.154%

    No Known Activations