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

    Neuronpedia

    INDEX
    Explanations

    transition phrases indicating a preference or alternative

    oai_token-act-pair · gpt-3.5-turbo

    the word "rather" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mberg
    -0.90
    }}}
    -0.67
    arent
    -0.65
    reen
    -0.64
    usha
    -0.63
    ayne
    -0.61
    amba
    -0.61
    kernel
    -0.60
    esville
    -0.60
    esian
    -0.59
    POSITIVE LOGITS
     than
    1.64
    than
    1.32
     Than
    1.13
     pathetic
    0.83
     omin
    0.82
     ironically
    0.82
     awkwardly
    0.81
     irritating
    0.80
     amusing
    0.79
     tame
    0.76
    Act Density 0.025%

    No Known Activations